Re: [Computer-go] AlphaGo Zero SGF - Free Use or Copyright?
Petri and Tom are correct; "intuition" and "subconscious" and "unobserved thought" are names for the same idea. AlphaGo Zero's neural network, regardless of how well it simulates human neurons or not, cannot be described as being similar to what we think of as the logical, rule-driven part of the human thought process; it is much more akin to the "intuition" or "subconscious" of a highly experienced player, wrapped together with a very logical process akin to what we humans call "reading." Terry McIntyre <terrymcint...@yahoo.com> Unix/Linux Systems Administration Taking time to do it right saves having to do it twice. On Sunday, October 29, 2017, 6:42:27 AM EDT, Petri Pitkanen <petri.t.pitka...@gmail.com> wrote: intuition is handy word for truly automated information processing i.e subconscious. And everything that train conscious decission making trains also the subconscious/intuiton. Intuiton nothing mythical just automation achieved via training 2017-10-29 5:08 GMT+02:00 Thomas Rohde <t...@bonobo.com>: On 2017-10-28 at 16:36, Robert Jasiek <jas...@snafu.de> wrote: > IMO, intuition does not exist; it is nothing but an excuse for not > understanding subconscious or currently unobservable thinking yet. Can we > speak of human subconscious thinking, please? Uhm, I always thought the short word for “subconscious thinking” was “intuition” ;-) Reminds me of “A Table is a Table” (orig. “Ein Tisch ist ein Tisch”), a short story by Swiss writer Peter Bichsel —> https://vimeo.com/11331609 (ten minutes video, English version) —> https://vimeo.com/8749843 (German version) “What's in a name? that which we call a rose By any other word would smell as sweet” — Shakespeare Greetings, Tom -- Thomas Rohde Wiesenkamp 12, 29646 Bispingen, GERMANY -- t...@bonobo.com __ _ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/ mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))
I'm sorry, did I miss soemthing here? On Friday, October 27, 2017, 5:46:19 AM EDT, Gian-Carlo Pascuttowrote: On 27-10-17 00:33, Shawn Ligocki wrote: > But the data should be different for different komi values, right? > Iteratively producing self-play games and training with the goal of > optimizing for komi 7 should converge to a different optimal player > than optimizing for komi 5. "For the policy (head) network, yes, definitely. It makes no difference to the value (head) network." The value network indicates whether the board leads to a win or not. This would certainly depend on komi, especially in the half-point games which seem to be the natural end result of how it selects moves? ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] dealing with multiple local optima
"seeing" is complex when the input is just a bunch of pixels. Terry McIntyre Unix/Linux Systems Administration Taking time to do it right saves having to do it twice. On Friday, February 24, 2017 12:32 PM, Minjae Kim <xive...@gmail.com> wrote: But those video games have a very simple optimal policy. Consider Super Mario: if you see an enemy, step on it; if you see a whole, jump over it; if you see a pipe sticking up, also jump over it; etc. On Sat, Feb 25, 2017 at 12:36 AM, Darren Cook <dar...@dcook.org> wrote: > ...if it is hard to have "the good starting point" such as a trained > policy from human expert game records, what is a way to devise one. My first thought was to look at the DeepMind research on learning to play video games (which I think either pre-dates the AlphaGo research, or was done in parallel with it): https://deepmind.com/research/ dqn/ It just learns from trial and error, no expert game records: http://www.theverge.com/2016/ 6/9/11893002/google-ai- deepmind-atari-montezumas- revenge Darren -- Darren Cook, Software Researcher/Developer My New Book: Practical Machine Learning with H2O: http://shop.oreilly.com/ product/0636920053170.do __ _ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/ mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] AlphaGo rollout nakade patterns?
blockquote, div.yahoo_quoted { margin-left: 0 !important; border-left:1px #715FFA solid !important; padding-left:1ex !important; background-color:white !important; } I speculate: nakade involves creating a shape (such as three in a row or a bulky five) such that, if captured, it would only form one eye, given the proper placement. I can imagine a set of patterns which enumerate the possibilities. Some examples exist, however, which are quite complex. Sent from Yahoo Mail for iPad On Monday, January 23, 2017, 11:45 AM, Roel van Engelenwrote: I am trying to re-create the fast rollout policy as described by deepMind but got stuck on the nakade patterns: "Nakade, # of patterns 8192: Move matches a nakade pattern at captured stone" the "at captured stone" confuses me, my first thought is: "this is only computed if stones have been captured recently" but i don't think that is correct. how should i read it? since they say "# of patterns 8192" i imagine they found some way to hash them just like the 3x3 and 12point diamond shapes but so fari have not found a way to do so. I found that other engines use heuristics to find nakade patterns so my question is does AlphaGo use patterns and does somebody know how this works? Thanks! Roel___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] Are the AlphaGols coming?
blockquote, div.yahoo_quoted { margin-left: 0 !important; border-left:1px #715FFA solid !important; padding-left:1ex !important; background-color:white !important; } During its training, AlphaGo played many handicap games against a previous version of itself, so the team and the program are acquainted with handicap play. I don't recall reading any discussion of komi experiments. Google's advantage is that they can dynamically spin up bunches of processors to try all sorts of experiments, including tournaments designed to test various versions, theories, and tweaks. There was some discussion about what to do if one could spin up thousands of processr cores on demand. There are surely large businesses in China which could do the same. They have similar reasons to pursue deep learning and other creative uses of big data and supercomputing. Sent from Yahoo Mail for iPad On Thursday, January 5, 2017, 9:36 PM, David Ongarowrote:This discussion reminds me of an incident which happened at the EGC in Tuchola 2004 (maybe someone can find a source for this). I don’t remember all details but it was about like this: Two amateur players where analyzing a Game and a professional player happened to come by. So they asked him how he would assess the position. After a quick look he said “White is leading by two points”. The two players where wondering: “You can count that quickly?”, but the pro answered “No, I just asked myself if I would like to have black in this position. The answer is no. But with two extra Komi for Black it would feel ok.” So it seems professionals already acquired some kind of “value network” due to their hard training, but they also can modify its assessments by taking Komi into account. Maybe that's something we also should do, i.e. not only train the value network by taking go positions and results into account but also add the Komi as an input (the output would still be a simple win/lose result). In that way we don’t have to train a different network for each Komi, even though the problem getting enough training data for all Komi values still remains. On Jan 5, 2017, at 11:44 AM, David Ongaro wrote: On Jan 5, 2017, at 2:37 AM, Detlef Schmicker wrote: Hi, what makes you think the opening theory with reverse komi would be the same as with standard komi? I would be afraid to invest an enormous amount of time just to learn, that you have to open differently in reverse komi games :) Thats why I used the comparative adjective “less”. It might not be ideal, but still much better than changing the fundamental structure of the opening with an extra stone. Furthermore the effect might not as big as you think: 1. The stronger player doesn’t have to play overplays when the handicap is correct. If the handicap is correct and if AlphaGo “knows” that is another question though… Of course the weaker player might play differently (i.e. more safely) but at least that is something he or she can control 2. One could even argue the other way around: we might see more sound (theoretically correct) moves from AlphaGo with reverse Komi. If it's seeing itself ahead already during the opening it might resort to slack but safe moves. Since it’s still winning we can be left wondering if it was actually a good move. But if it does an unusual looking move which it can’t be considered an overplay but it’s still winning in the end with reverse Komi there should be a real insight to gain. Still, a reverse Komi handicap is rather big, but it might be the next best thing we have without retraining the value network from scratch. Furthermore retraining the value network will probably affect the playing style even more. Thanks, David O. Am 05.01.2017 um 10:50 schrieb Paweł Morawiecki: 2017-01-04 21:07 GMT+01:00 David Ongaro : [...]So my question is: is it possible to have reverse Komi games by feeding the value network with reverse colors? In the paper from Nature (subsection "Features for policy/value network"), authors state: *the stone colour at each intersection was represented as either player or opponent rather than black or white. * Then, I think the AlphaGo algorithm would be fine with a reverse komi. Namely, a human player takes black and has 7.5 komi. The next step is that AlphaGo gives 2 stones of handicap but keeps 7.5 komi (normally you have 0.5). Aja, can you confirm this? Also having 2 stone games is not so interesting since it would reveal less insights for even game opening Theory. I agree with David here, most insights we would get from even games. But we can imagine the following show. Some games are played with a reverse komi, some games would be played with 2 stones (yet, white keeps 7.5 komi) and eventually the main event with normal even games to debunk our myths on the game. Wouldn't be super exciting!? Best regards, Paweł
Re: [Computer-go] it's alphago
It's one thing to know the recipe; it's another to have an industrial-size kitchen. Google was able to throw truly gargantuan amounts of computing resources at this problem. A few years back, a researcher - was it Remi Coulon? - was able to scrounge a few thousand cores for a tournament. Google designed an ASIC specifically for the task of accelerating their neural networks, and made thousands of them available for massive tests and training. Terry McIntyre <terrymcint...@yahoo.com> Unix/Linux Systems Administration Taking time to do it right saves having to do it twice.tr On Thursday, January 5, 2017 9:01 AM, Stefan Kaitschick <skaitsch...@gmail.com> wrote: Honestly I got a little frustrated that many people didn't think that was AlphaGo. It was almost clear to me because I know the difficulty of developing AlphaGo-like bots. I feel with you. People seem to think that the Nature paper gave away the full recipe. ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] Nice graph
blockquote, div.yahoo_quoted { margin-left: 0 !important; border-left:1px #715FFA solid !important; padding-left:1ex !important; background-color:white !important; } It's never wise to generalize too much from one data point. AlphaGo 2.0 is very very good at defeating AlphaGo 1.0. This does not make 2.0 a 10 dan pro. If it beat a succession of 9 dan pros, the claim would be credible. I think David Silver knows this. I think he and his team are studying Game 4 very closely, and are working on the 3.0 version. And I notice that all the top programs are taking a close look at DCNN now. Sent from Yahoo Mail for iPad On Friday, March 25, 2016, 7:48 PM, Petr Baudiswrote: The thread is http://www.lifein19x19.com/forum/viewtopic.php?f=18=12922=201695 On Fri, Mar 25, 2016 at 09:16:07PM -0400, Brian Sheppard wrote: > Hmm, seems to imply a 1000-Elo edge over human 9p. But such a player would > literally never lose a game to a human. > > I take this as an example of the difficulty of extrapolating based on games > against computers. (and the slide seems to have a disclaimer to this effect, > if I am reading the text on the left hand side correctly). Computers have > structural similarities that exaggerates strength differences in head-to-head > comparisons. But against opponents that have different playing > characteristics, such as human 9p, then the strength distribution is > different. I agree. Well, computer vs. computer may be still (somewhat) fine as long as it's different programs. What I wrote in that thread: The word covered by the speaker's head is "self". Bot results in self-play are always(?) massively exaggerated. It's not uncommon to see a 75% self-play winrate in selfplay to translate to 52% winrate against a third-party reference opponent. c.f. fig 7&8 in http://pasky.or.cz/go/pachi-tr.pdf . Intuitively, I'd expect the effect to be less pronounced with very strong programs, but we don't know anything precise about the mechanics here and experiments are difficult. It's no doubt today's AlphaGo is much stronger than the Nature version. But how much? We'll have a better idea when they pit it in more matches with humans, and ideally when other programs catch up further. Without knowing more (like the rest of the slides or a statement by someone from Deepmind), I wouldn't personally read much into this graph. -- Petr Baudis If you have good ideas, good data and fast computers, you can do almost anything. -- Geoffrey Hinton ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] Finding Alphago's Weaknesses
blockquote, div.yahoo_quoted { margin-left: 0 !important; border-left:1px #715FFA solid !important; padding-left:1ex !important; background-color:white !important; } According to the paper, AlphaGo did not use an opening book at all, in the version which played Fan Hui. Hypothetically, they could have grafted one on. I read a report that the first move in game 2 vs. Lee Sedol took only seconds. On the other hand, it's first move in game 1 took a longer while. We can only speculate. Sent from Yahoo Mail for iPad On Thursday, March 10, 2016, 12:31 PM, uurtamo .wrote: Quick question - how, mechanically, is the opening being handled by alpha go and other recent very strong programs? Giant hand-entered or game-learned joseki books? Thanks, steve On Mar 10, 2016 12:23 PM, "Thomas Wolf" wrote: My 2 cent: Recent strong computer programs never loose by a few points. They are either crashed before the end game starts (because when being clearly behind they play more desperate and weaker moves because they mainly get negative feadback from their search with mostly loosing branches and risky play gives them the only winning sequences in their search) or they win by resignation or win by a few points. In other words, if a human player playing AlphaGo does not have a large advantage already in the middle game, then AlphaGo will win whether it looks like it or not (even to a 9p player like Michael Redmond was surprised last night about the sudden gain of a number of points by AlphaGo in the center in the end game: 4:42:10, 4:43:00, 4:43:28 in the video https://gogameguru.com/alphago-2/) In the middle and end game the reduced number of possible moves and the precise and fast counting ability of computer programs are superior. In the game commentary of the 1st game it was mentioned that Lee Sedol considers the opening not to be his strongest part of the game. But with AlphaGo playing top pro level even in the opening, a large advantage after the middle game might simply be impossible to reach for a human. About finding weakness: In the absense of games of AlphaGo to study it might be interesting to get a general idea by checking out the games where 7d Zen lost on KGS recently. Thomas On Thu, 10 Mar 2016, wing wrote: One question is whether Lee Sedol knows about these weaknesses. Another question is whether he will exploit those weaknesses. Lee has a very simple style of play that seems less ko-oriented than other players, and this may play into the hands of Alpha. Michael Wing I was surprised the Lee Sedol didn't take the game a bit further to probe AlphaGo and see how it responded to [...complex kos, complex ko fights, complex sekis, complex semeais, ..., multiple connection problems, complex life and death problems] as ammunition for his next game. I think he was so astonished at being put into a losing position, he wasn't mentally prepared to put himself in a student's role again, especially to an AI...which had clearly played much weaker games just 6 months ago. I'm hopeful Lee Sedol's team has been some meta-strategy sessions where, if he finds himself in a losing position in game two, he turns it into exploring a set of experiments to tease out some of the weaknesses to be better exploited in the remaining games. On Thu, Mar 10, 2016 at 8:16 AM, Robert Jasiek wrote: > On 10.03.2016 00:45, Hideki Kato wrote: > > > such as solving complex semeai's and double-ko's, aren't solved yet. > > To find out Alphago's weaknesses, there can be, in particular, > > - this match > - careful analysis of its games > - Alphago playing on artificial problem positions incl. complex kos, > >complex ko fights, complex sekis, complex semeais, complex endgames, > >multiple connection problems, complex life and death problems (such as > Igo >Hatsu Yoron 120) etc., and then theoretical analysis of such play > - semantic verification of the program code and interface > - theoretical study of the used theory and the generated dynamic data > >(structures) > > -- > robert jasiek > ___ > Computer-go mailing list > Computer-go@computer-go.org > http://computer-go.org/mailman/listinfo/computer-go [1] Links: -- [1] http://computer-go.org/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@computer-go.org
Re: [computer-go] Re: Open source real time Go server
When SE fails, it is often blatantly obvious: a group is dead or in seki, but judged to be alive; or vice versa. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Open source real time Go server
It's all about expectations -- at this point, we don't expect any SE to say at move 10: This is a half-point win for white. ( I recall a pro making such an observation; I was willing to accept his expertise on the matter. ) But if it says at move 160: White wins by 5 points, it should be in the ballpark - or at least not so far out of the ballpark that a 16 kyu player wonders whether it might be playing in the wrong field entirely. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Open source real time Go server
If accessibility is the only criterion, a client would do the trick; it would need an open protocol. It's been a bit of an inconvenience that KGS does not publish an open-protocol interface. As for other things we'd like to see improved, we could build a list. My pet peeve is the KGS score estimator, which is often wildly wrong. I've heard complaints about the implementation of the rules, and some have argued that it is not terribly bot-friendly. Terry McIntyre terrymcint...@yahoo.com Everyone wants to live at the expense of the state. They forget that the state wants to live at the expense of everyone. --Frederic Bastiat ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Open source real time Go server
If the protocol isn't open, it can be changed. It is believed that wms did just that to frustrate open-source clients. There may be some justification to his argument that buggy clients were causing problems with his server. From: Michael Williams michaelwilliam...@gmail.com Even though KGS is not open, you can still reverse engineer it, right? Why not create an accessible web interface to KGS? terry mcintyre wrote: If accessibility is the only criterion, a client would do the trick; it would need an open protocol. It's been a bit of an inconvenience that KGS does not publish an open-protocol interface. As for other things we'd like to see improved, we could build a list. My pet peeve is the KGS score estimator, which is often wildly wrong. I've heard complaints about the implementation of the rules, and some have argued that it is not terribly bot-friendly. Terry McIntyre terrymcint...@yahoo.com __ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Open source real time Go server
When I say the SE is wildly off, I'm not referring to positions which only a pro could evaluate but positions which a double-digit kyu player could correctly evaluate. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] problem which current programs have difficulty solving
A high dan-level player ( to which our programs aspire ) would play it properly. I'm a mid-kyu player, and I find these solutions about half the time, and half not; that's why I am not a dan-level player, lol. GnuGo does have a method ( dragon status ) to explicitly ask is this group alive or dead? Correction to my post: the title is Rescue and Capture. From: Stefan Kaitschick stefan.kaitsch...@hamburg.de I wouldn't consider not solving this pathological. I think it's a pretty difficult problem. Without a problem warning most amateur players would miss it too. You can't force life and you can't force connection. The either-or is easy to miss. Stefan - Original Message - From: terry mcintyre To: computer go Sent: Sunday, December 20, 2009 7:03 PM Subject: [computer-go] problem which current programs have difficulty solving This gem is from one of Yilun Yang's little pocket-sized books - I think it is called Recovery And Connections. Neither Gnugo, Fuego, nor Many Faces of Go is able to solve it. Fuego came closest, recognizing the best black move, but a few moves later, it lost interest and played elsewhere. GnuGo rejects the winning move as unsafe. Btw, GoGui/Gnugo have a method to find dragon status; is there something comparable with Fuego/GoGui? Terry McIntyre terrymcint...@yahoo.com ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] problem which current programs have difficulty solving
This gem is from one of Yilun Yang's little pocket-sized books - I think it is called Recovery And Connections. Neither Gnugo, Fuego, nor Many Faces of Go is able to solve it. Fuego came closest, recognizing the best black move, but a few moves later, it lost interest and played elsewhere. GnuGo rejects the winning move as unsafe. Btw, GoGui/Gnugo have a method to find dragon status; is there something comparable with Fuego/GoGui? Terry McIntyre terrymcint...@yahoo.com “Politics should be limited in scope to war, protection of property, and the occasional precautionary beheading of a member of the ruling class.” P.J. O'Rourke test.sgf Description: Binary data ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Hahn system tournament and MC bots
From: Vlad Dumitrescu vladd...@gmail.com I'm sorry to bother you, but I don't get it. There must be some subtle detail that escapes me... Please try to explain why the hahn calculation isn't working in a normal game so as to ensure a win. I'm talking about strong human players. In my view, we have hahn: object of the game = max board score normal: object of the game = board score komi Both seem just as easy and interesting. If you are winning in the Hahn sense, your score also exceeds komi; but Hahn scoring - either by accumulating points in a tournament ranking, or converting points to dollars in bang neki fashion, gives you incentive to achieve larger scores. Under the board score komi regime, if you have a group which might be invaded (at some risk of losing points), but which can be safely walled off, I might choose to wall it off if my overall score is sufficient to win. Under Hahn scoring, a rational player would probably invade, in order to maximize the expected win. In some sense, half a point is good enough may be easier for such situations - the safe strategy is easier to compute; seal the borders and count, if you have enough, you're done. Smart players will economize - rich men don't pick fights - the game will progress to simpler, more easily-analyzed paths, where the outcome is certain. In a way, this is like an Indian parable: a sultan decreed that his daughter would be given in marriage to the slowest horse in a race among her suitors. In order to prevent the race from taking all day, he randomly assigned each suitor to ride a different suitor's horse. In regular go, rich men (winners) don't pick fights; losers do. In Hahn go, rich men pick fights, and losers seek to minimize their losses. I'd love to see a regular Hahn tournament among computer programs; it might lead to some interesting advances. Strong programs might become rapaciously bloodthirsty daredevils. They might develop models of opponents' weaknesses - learning that programs A and B always fall for certain swindles, but C and D do not. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Hahn system tournament and MC bots
In my experience, go players (I include myself) rarely count territory until they reach the low-kyu level. It's all about slaying dragons and adventure. Terry McIntyre terrymcint...@yahoo.com Anarchism is founded on the observation that since few men are wise enough to rule themselves, even fewer are wise enough to rule others. - Edward Abbey ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Hahn system tournament and MC bots
Perhaps computers play better (so far) when they focus on the wins because they are not omniscient; they can get suckered into thinking that large groups are alive or dead when the reverse is actually true. Humans are better at chunking life-and-death status of independent groups. ( Newell and Simon, Cognitive Science, Chunking hierarchies ) http://en.wikipedia.org/wiki/Chunking_%28psychology%29 Terry McIntyre terrymcint...@yahoo.com Anarchism is founded on the observation that since few men are wise enough to rule themselves, even fewer are wise enough to rule others. - Edward Abbey From: Don Dailey dailey@gmail.com To: computer-go computer-go@computer-go.org Sent: Mon, November 23, 2009 8:21:15 AM Subject: Re: [computer-go] Re: Hahn system tournament and MC bots I have repeatedly stated that the Hahn system is a simplification, but this is just a guess on my part and I might have it backwards.I'm not sure whether that invalidates the idea that computers will play this better or not. Here is a thought experiment.Imagine an omniscient player or program which is capable of always playing the very best move according to either criteria that you configure.You can configure it maximize the score, or to win the game. In win game mode it will play ANY move randomly that is good enough. Since it is omnicient there is no point in talking about risk, or chances in any context. In a lost game it would play a move at random. In maximize score mode it would choose the move that maximizes the total points taken on the board. It would be the perfect Hahn system player for instance. The more difficult strategy is to maximize total points on the board.In fact, this is a superset of the other strategy because maximizing the points taken will always be a valid way to implement the try to win game strategy, but the reverse is not true. This is no doubt why computers play stronger with the goal to win the game - it is a much less distracting concept for a computer to grasp. So I am not sure, but I might be reversing my point of view on this.I have to think about it some more. It's clear that computers play weaker with this strategy, but I'm still pretty sure they will play the Hahn system better with the maximize points taken strategy but it may not follow that they will play this better relative to humans.Especially if it is a more challenging goal. What I cannot decide is if it is really more challenging - I just know it's more challenging to do it perfectly. - Don On Mon, Nov 23, 2009 at 11:00 AM, Robert Jasiek jas...@snafu.de wrote: steve uurtamo wrote: the idea that i like about keeping track of number of points won or lost by is that not only could you find the winner, but you could find how absolutely dominant, on average, they were against their opponents. Under normal Go: no! E.g., some players have the style to let every game be close. -- robert jasiek ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Hahn system tournament and MC bots
see http://senseis.xmp.net/?BangNeki Terry McIntyre terrymcint...@yahoo.com Anarchism is founded on the observation that since few men are wise enough to rule themselves, even fewer are wise enough to rule others. - Edward Abbey ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Shodan Go Bet: Nov '09 Update
Any hardware which can be brought to the playing site would presumably include today's baby supers, which include a few dozen cores in a desktop box. Would it include whatever fits into Sun's datacenter-in-a-shipping-container? I am less optimistic about the computer's prospects now than I was two years ago. Terry McIntyre terrymcint...@yahoo.com Anarchism is founded on the observation that since few men are wise enough to rule themselves, even fewer are wise enough to rule others. - Edward Abbey ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Elo move prediction
It may be helpful to incrementally compute information on a move-by-move basis, rather than recompute for all points on the board. For example; if you choose to store the liberties of groups, and a single stone is placed on the board, it affects only those strings which have thereby lost a liberty. It may lead to combining two or more strings. It may also lead to a capture, which creates liberties -- but captures are much less frequent than non-capturing moves, so it pays to optimize the non-capturing move heavily. Similar approaches may work for whatever else is being measured. If one stone is played at a time, what does this change? Recomputing anything 361 times for each move of each playout is likely to be sluggish. Terry McIntyre terrymcint...@yahoo.com Anarchism is founded on the observation that since few men are wise enough to rule themselves, even fewer are wise enough to rule others. - Edward Abbey ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Go Programming Language
Perhaps it is time to switch to the Korean name, baduk? Terry McIntyre terrymcint...@yahoo.com Anarchism is founded on the observation that since few men are wise enough to rule themselves, even fewer are wise enough to rule others. - Edward Abbey From: Michael Williams michaelwilliam...@gmail.com To: computer-go computer-go@computer-go.org Sent: Wed, November 11, 2009 3:49:46 PM Subject: Re: [computer-go] Go Programming Language If you thought finding Go(game)-related stuff on the web was hard before... Ben Shoemaker wrote: Has anyone tried programming Go in the Go Programming Language? http://golang.org/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Joseki Book
Robert, Your post is the first usage of sum-style that I have seen -- and I haven't turned up anything at senseis.xmp.net. What is sum-style? Can you elucidate? Do I have to read the book? Thanks! Terry McIntyre terrymcint...@yahoo.com Anarchism is founded on the observation that since few men are wise enough to rule themselves, even fewer are wise enough to rule others. - Edward Abbey From: Robert Jasiek jas...@snafu.de To: computer-go computer-go@computer-go.org Sent: Tue, November 10, 2009 1:04:12 PM Subject: Re: [computer-go] Re: Joseki Book Ingo Althöfer wrote: ... I do not mention some obvious mistakes. Are they later in the game(s), or also some in the openings? Also some during the opening. (Every dan player can point them out to you. Ask those that can distinguish sum-style from obvious mistakes.) -- robert jasiek ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Joseki Book
When building a joseki database, there is a caveat which may not be obvious to kyu-level players: Some joseki sequences depend upon ladder relationships. When the ladder succeeds, the joseki move may be brilliant. When the ladder fails, the same sequence leads to disaster. Smart opponents will pick the sequence which leads to disaster for you, if you give them a chance. MCTS may not detect such sequences, since they often require very precise order of play. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [SPAM] Re: [computer-go] Joseki Book
One approach might be to combine some well-known joseki and fuseki books with such books as 100 tips for Amateur Players, which explain some of the pitfalls, tricks, and traps behind popular joseki. Nihon Kiin publishes some detailed and thorough joseki books. Slate and Shell published a series of workbooks by Yilun Yang; one of those suggests a few guidelines for when to tenuki, that is, when it is ok for one to ignore an approach move and play elsewhere. These might help guide a program to know when to stay on the main line of a joseki, and when to switch to another important point. There is a proverb, study joseki, lose two stones.(in strength) I don't know if anybody has used MCTS to blend local joseki knowledge with strategic knowledge to determine which joseki is most appropriate; that might be an interesting line of approach. If you store the joseki as a tree, it might make sense to expand not just one, but the several main lines in the tree, then compare their merits. One might even expand the trick play lines. I once was told by a Japanese Go professional that he was given two very strict commands when he began studying as an insei. The first was, never, ever study joseki. The second was, never ever play his father. ( who was a 3 P professional ). ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Joseki Book
From: Alain Baeckeroot alain.baecker...@laposte.net Le 09/11/2009 à 08:04, Jessica Mullins a écrit : Hi, I am wondering what is the best way to build a Joseki Book? I am a student at Lewis Clark College and am working with Professor Peter Drake to build a Joseki Book for the program Orego. Right now I am extracting moves from professor players and saving those into a database. Then if during game play a position is contained in the database, play the response move like the professional. I am just wondering what other people have done to build a Joseki Book, or if anyone knows of any papers that might be helpful. I don't knwo how to build such a book, but Kogo's Joseki dictionnary is a huge .sgf file containging joseki + trick moves and punishment. Maybe it can be parsed to extract only joskis. I have been told by stronger players that Kogo, while a useful starting point, needs to be supplemented with newer lines of play. Regarding automatic extraction of joseki from pro games - the one pitfall I see is that you'll only discover the surface of a much deeper tree of moves which don't appear in pro games - how best to respond to non-joseki plays. A move is joseki because sound refutations to non-joseki plays exist, but those refutations can be subtle; a characteristic of a trick play is that the refutation is difficult for weaker players. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [SPAM] Re: [computer-go] First ever win of a computer against a pro 9P as black (game of Go, 9x9).
That sounds to me like a dumb human with a smart algorithm can beat a fast computer with a dumb algorithm -- which speaks more to Penrose's reluctance to improve algorithms in his dumbed-down computer models than it does to any quantum-physical effects. Stir in some theorem-proving ability - where a great deal of research was accomplished decades ago - and a computer chess program can prove theorems about chess positions, including these bishops can never get past these pawns. This may be useful in computer Go. One of the reasons human pros do well is that they compute certain sub-problems once, and don't repeat the effort until something important changes. They know in an instant that certain positions are live or dead or seki; they know when a move ( reducing a liberty, for example ) disturbs that result. This could probably be emulated with theorem-proving ability. Presently, search algorithms have to rediscover these results many times over; this is (in my opinion) why computer programs get significantly weaker when starved for time; they cannot think deeply enough to solve problems which may be solved in an eyeblink by a pro. I've observed some high-dan-level amateurs playing complex semeai on 19x19 games. They might not actually know the result of a semeai, but they respond quickly to moves which would alter the status - if one of my liberties is taken, I take one of his - until such point as the player takes a noticeably long time to re-analyse the semeai and think I need not respond to that move and takes sente. The stronger the player, the more accurate these assessments are. Terry McIntyre terrymcint...@yahoo.com And one sad servitude alike denotes The slave that labours and the slave that votes -- Peter Pindar From: Mark Boon tesujisoftw...@gmail.com To: computer-go computer-go@computer-go.org Sent: Thu, October 29, 2009 10:14:18 AM Subject: Re: [SPAM] Re: [computer-go] First ever win of a computer against a pro 9P as black (game of Go, 9x9). Roger Penrose thinks the human brain can do things a Turing machine cannot. (Note: I don't say 'computer'.) He claims it's due to some quantum-physical effects used by the brain. I doubt his ideas are correct, but he did have a few interesting chess-positions to support his theory. Typically, they would contain a completely locked position, say a V-shaped pawn position and bishops on the wrong color to pass the pawn-ranks. These types of positions are very easily analyzed by even mediocre players, yet a computer never gets the right answer. Basically what it shows is that the human brain is able to conceptualize certain things that enable it to reason about situations that cannot be calculated by brute force. I don't claim that a Turing machine cannot do such things as well if programmed well, but it's very easy to see that there could be barriers to computers, no matter how much computing power you give them, if they solely rely on a simple method with brute force. Mark ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Congratulations to AyaMC!
Is there a way to implement I don't understand that command? a NAK, perhaps? Terry McIntyre terrymcint...@yahoo.com And one sad servitude alike denotes The slave that labours and the slave that votes -- Peter Pindar From: Nick Wedd n...@maproom.co.uk To: computer-go computer-go@computer-go.org Sent: Tue, October 6, 2009 9:13:17 AM Subject: Re: [computer-go] Congratulations to AyaMC! In message wladvtgcx1ykf...@maproom.demon.co.uk, Nick Wedd n...@maproom.co.uk writes Congratulations to AyaMC, winner of Sunday's KGS Computer Go tournament! My report is at http://www.weddslist.com/kgs/past/52/index.html Two people had bots crash after receiving the message FINEST: Still an outstanding command. I do not know what this means, and am reporting it to wms. I have heard back from wms: The still an outstanding command message means that a command has been sent to the engine, but the engine hasn't yet answered it. That's probably a bug in the engine, because GTP requires all commands to be answered with an acknowledgement or an error. So it seems that CzechBot (=MoGo) and Fuego need to implement something, I don't know what. It's strange that this has never come up before. Nick -- Nick Weddn...@maproom.co.uk ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Generalizing RAVE
From: Brian Sheppard sheppar...@aol.com I have another way to fail to improve on RAVE. :-) Well, that's great news. Thomas Edison was once asked if he felt discouraged by 10 thousand failed experiments, and he said Not at all; I now know ten thousand ways to not build an electric light bulb. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Generalizing RAVE
Peter Drake wrote: The more I study this and try different variants, the more impressed I am by RAVE. Boards after the current board is a very clever way of defining similarity. Also, recorded RAVE playouts, being stored in each node, expire in an elegant way. It still seems that RAVE fails to exploit some sibling information. For example, if I start a playout with black A, white B, and white wins, I should (weakly) consider B as a response to any black first move. Yamato replied: It is exactly the same as my thought. I also have tried CRAVE, but the results were worse than normal RAVE. While RAVE is a very efficient algorithm, it strongly limits scalability of the program. It typically makes a fatal mistake in the position that the order of moves are important. We definitely need to improve RAVE, but it is a very tough job. Indeed it is. How may a program reason about the order of moves? At higher levels of play, the order of moves is often crucial. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Dead stones in human-bot games
Is there no way for the bot to dispute the other player's decision? I recall something of the sort in human-to-human play -- both have to agree before the scoring phase. I do not know whether the KGS API works the same way. Terry McIntyre terrymcint...@yahoo.com And one sad servitude alike denotes The slave that labours and the slave that votes -- Peter Pindar From: Peter Drake dr...@lclark.edu To: Computer Go computer-go@computer-go.org Sent: Thursday, September 17, 2009 1:52:07 PM Subject: [computer-go] Dead stones in human-bot games Orego has been doing well in 9x9 games on KGS, using the fast time controls of this weekend's upcoming tournament. I even improved the endgame behavior a bit: Orego will pass if (a) the opponent has passed first, and (b) after removing Orego's dead stones, but not the opponent's, Orego still wins. This means that Orego won't always play until there are no legal moves. I looked at one of the lost games (attached), and found that (if I'm reading this correctly) the human won simply by marking all of Orego's (white) stones dead. Do bots automatically defer to humans when there are disputes? Isn't there supposed to be a cleanup phase? Would it be the same in a rated game? Peter Drake http://www.lclark.edu/~drake/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] any mac programmers out there?
Cool! Have you had a chance to experiment with the gcc-llvm and clang versions of fuego? From: David Doshay ddos...@mac.com The best way to do it is to use darwinports to install the boos libs. That means installing the ports infrastructure first and using it to install boost. I just finished doing it last week and Fuego compiles on my Mac laptop. Cheers, David On 7, Sep 2009, at 11:17 PM, Mark Boon wrote: Just being curious I decided to give it a swing to see if Fuego would compile on a Mac. The configure scripts stops saying 'boost' is not installed. So I downloaded the latest version of that (it's huge!) and set a BOOST_ROOT environment variable, but it still says it can't find it. Anyone know what's the matter there? I must admit I didn't spend a whole lot of time trying to figure it out. Mark ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] any mac programmers out there?
Found an interesting article on Snow Leopard at Ars Technica ... 20-some pages. http://arstechnica.com/apple/reviews/2009/08/mac-os-x-10-6.ars Of interest to Computer Go programmers: the addition of blocks to C, which allow closures and other fun stuff, much like Lisp. LLVM, which allows JIT compilation to multiple architectures, including GPUs; Grand Central Dispatch, which provides very light-weight concurrency; and CLANG, a new compiler which is said to be quite an improvement over GCC. Open CL, which leverages LLVM to program GPUs. Terry McIntyre terrymcint...@yahoo.com And one sad servitude alike denotes The slave that labours and the slave that votes -- Peter Pindar ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] any mac programmers out there?
From: Jason House jason.james.ho...@gmail.com On Sep 5, 2009, at 10:41 AM, terry mcintyre terrymcint...@yahoo.com wrote: Found an interesting article on Snow Leopard at Ars Technica ... 20-some pages. http://arstechnica.com/apple/reviews/2009/08/mac-os-x-10-6.ars Of interest to Computer Go programmers: the addition of blocks to C, which allow closures and other fun stuff, much like Lisp. D and C# are other C-family languages with similar. LLVM, which allows JIT compilation to multiple architectures, including GPUs; Grand Central Dispatch, which provides very light-weight concurrency; and CLANG, a new compiler which is said to be quite an improvement over GCC. Łukasz reported a 15% performance drop for libego when moving from gcc to llvm. llvm is under heavy development; it has probably improved since. Also, any new technology has both strong and weak points; it takes time to learn how to optimally fit an algorithm to a compiler. Apple reports that recent versions of llvm outperform gcc. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] MoGo policy: capture stones anywhere?
If you maintain a list of strings ( connected groups ) of stones and their liberty counts - or perhaps the actual liberties - it should be fairly quick to find a string with just one liberty. In any case, if I read the explanation correctly, this happens infrequently, if several less-expensive tests fail; the cost would be amortized over many trials. Terry McIntyre terrymcint...@yahoo.com And one sad servitude alike denotes The slave that labours and the slave that votes -- Peter Pindar From: Peter Drake dr...@lclark.edu To: Computer Go computer-go@computer-go.org Sent: Monday, August 31, 2009 9:56:16 PM Subject: [computer-go] MoGo policy: capture stones anywhere? MoGo's playout policy (at one time) is given in section 3.2 of Gelly et al's paper, Modification of UCT with Patterns in Monte-Carlo Go: We describe briefly how the improved random mode generates moves. It first verifies whether the last played move is an Atari; if yes, and if the stones under Atari can be saved (in the sense that it can be saved by capturing stones or increasing liberties), it chooses one saving move randomly; otherwise it looks for interesting moves in the 8 positions around the last played move and plays one randomly if there is any; otherwise it looks for the moves capturing stones on the Go board, plays one if there is any. At last, if still no move is found, it plays one move randomly on the Go board. We've implemented much of this, which has made Orego considerably stronger. The problem is with this part: otherwise it looks for the moves capturing stones on the Go board Does this really mean traversing the entire board looking for captures? Doing so seems to create a catastrophic speed hit. Peter Drake http://www.lclark.edu/~drake/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] congrats to Fuego! from US Go email
FUEGO BEATS PRO IN 9X9 EVEN GAME: The Fuego computer go program won a 9x9 even game against 9-dan professional Chou Chun-Hsun (Zhou Junxun, left) at the Human vs. Computer Program Competition (FUZZ-IEEE 2009) event held August 21-22 on Jeju Island, Korea. Fuego played three official games with Zhou, winning the first - taking white -- by 2.5 points. This is the first time that a computer program has won a 9x9 game on even against a top-ranked player. Everybody considers the win of Fuego in 9x9 as very good, said Olivier Teytaud, leader of the MoGo team. No error from the pro, just a perfect play by the computer. Click here for the game record. The Fuego team includes Markus Enzenberger, Broderick Arneson, Rich Segal (IBM) and Gerry Tesauro (IBM). The Japanese program Zen also put in a very strong performance, beating amateur Chang Shen-Su 6d with both Black and White on 9x9. The other two computer participants, MoGo and Many Faces of Go, did not win any games; click here for full results. I would like to thank everyone who helped, says Martin Mueller, especially Steve Sutphen for getting Fuego set up on the cluster, and Jonathan Schaeffer for financial support, and for allowing us to use his machine with its 80 cores. - photo of Chou Chun-Hsun by Jimmy Lin Terry McIntyre terrymcint...@yahoo.com And one sad servitude alike denotes The slave that labours and the slave that votes -- Peter Pindar ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Dynamic komi at high handicaps
Consider the game when computer is black, with 7 stones against a very strong human opponent. Computer thinks every move is a winning move; it plays randomly; a half-point win is as good as a 70-point win. Pro gains ground as computer makes slack moves, taking slightly less than its full due. At some point, the computer, being the weaker player, makes one slack move too many and loses the game. Rinse and repeat. At some point, it dawns on the programmer: must attack to win handicap games. Must be a little bit greedy, to slow down the process of attrition. Dynamic komi models something real: the significant advantage of the computer in a handicap game. It tries to preserve as much of that advantage as possible. I don't know if it will work for computer vs human games. I do know that a similar idea helped me defeat a human player and reduce my handicap by 3 stones. Not having the patience for thousands of 30-minute games to achieve statistically valid results, I settled for trouncing my opponent three games in a row by a large margin, then doing it again with a smaller handicap for three more games. I can't win by 70 stones in a 7 stone game, but 20 or 30 was enough to prove my point. If I made random plays under the assumption that I still had a half-point win, my opponent's predictive powers would be superior to mine - that's why he gives me a handicap and not vice versa. I can't really be sure that my prediction of a 22.5 point win is exact to the last decimal point - but if it should be within 5 or 10 or even 20, I'm perfectly happy. It's nice that statistics of a series of one-bit values are so useful, but when a significant fraction of those one-bit values are 100% wrong, that introduces a bit of noise to one's estimates. One hopes that they balance evenly, but perhaps they do not. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Don Dailey dailey@gmail.com To: computer-go computer-go@computer-go.org Sent: Wednesday, August 19, 2009 6:03:50 AM Subject: Re: [computer-go] Dynamic komi at high handicaps One must decide if the goal is to improve the program or to improve it's playing behavior when it's in a dead won or dead lost positions. It's my belief that you can probably cannot improve the playing strength soley with komi manipulation, but at a slight decrease in playing strength you can probably improve the behavior, as measured by a willingness to fight for space that is technically not relevant to the goal of winning the game.And only then if this is done carefully. However I believe there are better ways, such a pre-ordering the moves. Even if this can prove to be a gain, you are really working very hard to find something that only kicks in when the game is already decided - how to play when the game is already won or already lost.But only the case when the game is lost is this very interesting from the standpoint of making the program stronger. And even this case is not THAT interesting, because if you are losing, on average you are losing to stronger players. So you are working hard on an algorithm to beat stronger players when you are in a dead lost game? How much sense does that make? So the only realistic pay-off here is how to salvage lost games against players that are relatively close in strength since you can expect not to be in this situation very often agaist really weak players.So you are hoping to bamboozle players who are not not weaker than you - in situations where you have been bamboozled (since you are losing, you are the one being outplayed.) That is why I believe that at best you are looking at only a very minor improvement.If I were working on this problem I would be focused only on the playing style, not the playing strength. If you want more than the most minor playing strength improvement out of this algorithm, you have to start using it BEFORE the loss is clear, but then you are no longer playing for the win when you lower your goals, you are playing for the loss. - Don 2009/8/19 Stefan Kaitschick stefan.kaitsch...@hamburg.de One last rumination on dynamic komi: The main objection against introducing dynamic komi is that it ignores the true goal of winning by half a point. The power of the win/loss step function as scoring function underscores the validity of this critique. And yet, the current behaviour of mc bots, when either leading or trailing by a large margin, resembles random play. The simple reason for this is that either every move is a win or every move is a loss. So from the perspective of securing a win, every move is as good as any other move. Humans know how to handle these situations. They try to catch up from behind, or try to play safely while defending enough of a winning margin. For a bot
Re: [computer-go] Erlang and computer go
Peter Drake, I know Orego was written in Java. How do you handle memory allocation? Is there an equivalent of the C method of pre-allocating a large chunk and managing the nodes internally, instead of billions of alloc/free cycles? Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Don Dailey dailey@gmail.com To: computer-go computer-go@computer-go.org Sent: Friday, August 14, 2009 2:25:06 PM Subject: Re: [computer-go] Erlang and computer go I don't think JVM performance will be an issue for this.I assumed that you were willing to sacrifice a small amount of speed for a high level prototyping language and I think you will only get about 20-30% slowdown over C - I'm judging this by the performance of the reference bots I did in both java and C. You are probably not going to get any closer than this with any other high level language. If you like lispy languages there is something called bitc which is supposed to be pretty close to C in speed and there is also D, which has the potential to be faster than C - although it isn't right now.D would probably be a little closer to C speed than Java or Scala. My issue with Java and JVM is the memory hog nature and pathetic startup times - which make it FEEL slow and unresponsive, but in actuality it is pretty fast. I have found that java doesn't play well with memory - I would not use Java (or Scala) if you plan to do the big memory thing with MCTS, which likes efficient memory management and lots of space for nodes. But I cannot say for sure that this won't work. I don't understand Java enough and maybe there are data structures that you can preallocate in unboxed fashion that will be efficient.But my sense of things is that a node is going to be pretty fat. Honestly, I think your decision to stay with C is likely to be best. I don't even consider anything else when I look at a project that I think is going to need serious performance and memory requirements. - Don On Fri, Aug 14, 2009 at 5:07 PM, Carter Cheng carter_ch...@yahoo.com wrote: Thanks both I guess I will stick with C/C++ for now. I have looked at Scala before though not in this particular context. It looks like a pretty compelling language with some pretty nice features (true lambda functions, argument pattern matching among others). JVM performance does concern me however. I do have a followup question but I will make a separate topic of it. --- On Fri, 8/14/09, Vlad Dumitrescu vladd...@gmail.com wrote: From: Vlad Dumitrescu vladd...@gmail.com Subject: Re: [computer-go] Erlang and computer go To: computer-go computer-go@computer-go.org Date: Friday, August 14, 2009, 1:56 PM On Fri, Aug 14, 2009 at 22:16, Carter Chengcarter_ch...@yahoo.com wrote: I have been considering experimenting with Erlang as a means of prototyping certain aspects of a computer go program and I was curious if anyone has tried this already. How does a system like Erlang compare performance wise to writing something in say C/C++ (fastest) or Java? Hi, I have started for some year ago to try to withe an Erlang library to play go, but got distracted by other stuff. Erlang has a lot of nice features, but in this particular instance speed isn't one of them. The main issue is that there are no mutable data structures, so for all processing there will be a lot of copying. This is somewhat simplified, of course, but the conclusion still holds. I don't have any hard numbers, it would depend very much upon the choice of data structure. Erlang would be good at coordinating work done by simple and fast slaves, written in C for example. It would be very appropriate for a distributed engine. The problem here is that the problem of synchronizing a distributed UCT tree hasn't been solvet yet, to my knowledge. regards, Vlad ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Dynamic komi at high handicaps
One reason dynamic komi seems a bit odd is that the numbers are pulled out of thin air. Why should the komi be X instead of Y? When should the value be changed? Going back to the original thought experiment: the komi at the start of the game should reflect the expert assessment of how far ahead black is compared to white. A rational program should periodically change that assessment, as black blunders through the game. So, my next question is, what sort of experimentation has been done to assess the likely score at various parts of the game? Any results? It seems natural that a strong player, looking at a lot of handicap stones, will recognize that the position against an equally strong player would entail a loss - but of about n*10 stones, not of n*20 stones - and set an interim goal to acquire that much, while leaving opportunities for black to fumble. As such fumbles occur, white opportunistically consolidates more territory, and expectations are adjusted upwards -- only a 40 point loss now ... only 10 points now ... striking distance ... black is torpedoed now! ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Dynamic komi at high handicaps
The dynamic komi is perhaps a misnomer; it's by accident that changing komi reflects something which we do want to measure, namely the predicted score. An algorithm which does not make use of the predicted score would not make use of all available information. On a 19x19 board, it is common for some areas to become settled; whether unconditionally alive, or ( more likely ) alive under the assumption of alternating play. Many moves trade the prospect of territory here versus there. Bad moves give up too much for too little. Good moves exploit bad or slack moves, and provide an equitable balance against good play. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Don Dailey dailey@gmail.com To: computer-go computer-go@computer-go.org Sent: Thursday, August 13, 2009 9:27:11 AM Subject: Re: [computer-go] Dynamic komi at high handicaps 2009/8/13 Stefan Kaitschick stefan.kaitsch...@hamburg.de Modeling the opponents mistakes is indeed an alternative to introducing komi. But it would have to be a lot more exact than simply rolling the dice or skipping a move here and there. Successful opponent modeling would implement the overplay school of thought - playing tactically refutable combinations that are beyond the opponents skill to punish them. I cannot believe you are being so technically precise about doing this correctly while advocating something on the other hand which is so obviously incorrect. You probably have something here though.I think the play-out policy is a more fruitful area to explore than dynamically changing komi. I would start simple, just trying the simplest approach first then gradually refining it. Random occasional pass moves is certainly easy to implement as a first step. - Don Introducing komi at the 50% win rate level would implement the honte school of thought - play as if against yourself. At a win rate of less than 50% it implements the almost honte school of thought. :-) I'm not trying to moralize. In love and go anything is fair. I'm just saying that while both approaches are legitimate, adjusting the komi is much easier to do. Different subject, suggestion for a komi adjustment scheme: 1. Make a regular evaluation(no extra komi) 2. If the win rate of the best move is within certain bounds you're done (Say between 30 and 70 percent.Just a guess ofcourse.Also, this might shift as the game progresses) 3. If not, make a komi adjustment dependant on how far out of bounds the win rate is. (No numerical suggestion here. Please experiment.) 4. Make a new search with this komi. 5. If the new result is in bounds calculate winrate_nokomi * factor + winrate_komi for each candidate and choose the highest one. (factor around 10 maybe) 6. If not, go back to 3 The idea is to choose a move that doesnt contradict the long term goal(no komi search) while trying for a short term goal(komi search) if no long term goal is available.( Or if every move satisfies the long term goal in case of taking handicap) Stefan - Original Message - From: Don Dailey To: tapani.ra...@tkk.fi ; computer-go Sent: Thursday, August 13, 2009 4:02 PM Subject: Re: [computer-go] Dynamic komi at high handicaps This idea makes much more sense to me than adjusting komi does.At least it's an attempt at opponent modeling, which is the actual problem that should be addressed. Whether it will actually work is something that could be tested. Another similar idea is not to pass but to play some percentage of random moves - which probably would work in programs with strong playout strategies. Of course this would be meaningless for bots that have weak (and already random) playout strategies. - Don On Thu, Aug 13, 2009 at 6:17 AM, Tapani Raiko pra...@cis.hut.fi wrote: I don't think the komi should be adjusted. Instead: Wouldn't random passing by black during the playouts model black making mistakes much more accurately? The number of random passes should be adjusted such that the playouts are close to 50/50. Adjusting the komi would make black play greedily, while random passing during playouts would make black play safe (rich men don't pick fights). Tapani Raiko Christoph Birk wrote: I think you got it the wrong way round. Without dynamic komi (in high ha ndicap games) even trillions of simulations with _not_ find a move that creates a winning line, because the is none, if the opponet has the same strength as you. WHITE has to assume that BLACK will make mistakes, otherwise there would be no handicap. Christoph ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ -- Tapani Raiko, tapani.ra
Re: [computer-go] Dynamic komi at high handicaps
I have never heard a pro say I estimate my chances of winning this game to be 50.3%, but you will hear black is ahead by 3 points or white wins by 1/2 point. -- they'll make this evaluation based on the alternation of equally competent play. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Don Dailey dailey@gmail.com To: computer-go computer-go@computer-go.org Sent: Thursday, August 13, 2009 10:20:58 AM Subject: Re: [computer-go] Dynamic komi at high handicaps 2009/8/13 terry mcintyre terrymcint...@yahoo.com The dynamic komi is perhaps a misnomer; it's by accident that changing komi reflects something which we do want to measure, namely the predicted score. An algorithm which does not make use of the predicted score would not make use of all available information. You imply that it's some kind of travesty not to make use of available information, but the information is only available because you did extra work to generate it. And even if the information was free, it matters that you use it correctly. Just implying that it's wrong not to do this because you are throwing away available information is not going to cut it. On a 19x19 board, it is common for some areas to become settled; whether unconditionally alive, or ( more likely ) alive under the assumption of alternating play. Many moves trade the prospect of territory here versus there. Bad moves give up too much for too little. Good moves exploit bad or slack moves, and provide an equitable balance against good play. I think you have describe very well why dynamic komi is so hard. You take ALL these factors and ignore them all except for a single number. You don't know anything about the composition of that number.If your concern is about throwing away infromation, then dynamic komi should be a big problem for you. - Don Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Don Dailey dailey@gmail.com To: computer-go computer-go@computer-go.org Sent: Thursday, August 13, 2009 9:27:11 AM Subject: Re: [computer-go] Dynamic komi at high handicaps 2009/8/13 Stefan Kaitschick stefan.kaitsch...@hamburg.de Modeling the opponents mistakes is indeed an alternative to introducing komi. But it would have to be a lot more exact than simply rolling the dice or skipping a move here and there. Successful opponent modeling would implement the overplay school of thought - playing tactically refutable combinations that are beyond the opponents skill to punish them. I cannot believe you are being so technically precise about doing this correctly while advocating something on the other hand which is so obviously incorrect. You probably have something here though.I think the play-out policy is a more fruitful area to explore than dynamically changing komi. I would start simple, just trying the simplest approach first then gradually refining it. Random occasional pass moves is certainly easy to implement as a first step. - Don Introducing komi at the 50% win rate level would implement the honte school of thought - play as if against yourself. At a win rate of less than 50% it implements the almost honte school of thought. :-) I'm not trying to moralize. In love and go anything is fair. I'm just saying that while both approaches are legitimate, adjusting the komi is much easier to do. Different subject, suggestion for a komi adjustment scheme: 1. Make a regular evaluation(no extra komi) 2. If the win rate of the best move is within certain bounds you're done (Say between 30 and 70 percent.Just a guess ofcourse.Also, this might shift as the game progresses) 3. If not, make a komi adjustment dependant on how far out of bounds the win rate is. (No numerical suggestion here. Please experiment.) 4. Make a new search with this komi. 5. If the new result is in bounds calculate winrate_nokomi * factor + winrate_komi for each candidate and choose the highest one. (factor around 10 maybe) 6. If not, go back to 3 The idea is to choose a move that doesnt contradict the long term goal(no komi search) while trying for a short term goal(komi search) if no long term goal is available.( Or if every move satisfies the long term goal in case of taking handicap) Stefan - Original Message - From: Don Dailey To: tapani.ra...@tkk.fi ; computer-go Sent: Thursday, August 13, 2009 4:02 PM Subject: Re: [computer-go] Dynamic komi at high handicaps This idea makes much more sense to me than adjusting komi does.At least it's an attempt at opponent modeling, which is the actual problem that should be addressed. Whether it will actually work is something that could be tested. Another similar idea
Re: [computer-go] Dynamic komi at high handicaps
Ingo suggested something interesting - instead of changing the komi according to the move number, or some other fixed schedule, it varies according to the estimated winrate. It also, implicitly, depends on one's guess of the ability of the opponent. An interesting test would be to take an opponent known to be weaker, offer it a handicap, and tweak the dynamic komi per Ingo's suggestion. At what handicap does the ratio balance at 50:50? Can the number of handicap stones be increased with such an adaptive algorithm? Even better, play against a stronger opponent; can one increase the win rate versus strong opponents? The usual range of computer opponents is fairly narrow. None approach high-dan levels on 19x19 boards - yet. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Brian Sheppard sheppar...@aol.com To: computer-go@computer-go.org Sent: Wednesday, August 12, 2009 12:33:13 PM Subject: [computer-go] Dynamic komi at high handicaps The small samples is probably the least of the problems with this. Do you actually believe that you can play games against it and not be subjective in your observations or how you play against it? These are computer-vs-computer games. Ingo is manually transferring moves between two computer opponents. The result does support Ingo's belief that dynamic Komi will help programs play high handicap games. Due to small sample size it isn't very strong evidence. But maybe it is enough to induce a programmer who actually plays in such games to create a more exhaustive test. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Dynamic komi at high handicaps
Consider this thought experiment. You sit down at a board and your opponent has a 9-stone handicap. By any objective measure of the game, you should resign immediately. All your win-rate calculations report this hopeless state of affairs. Winrate gives you no objective basis to prefer one move or another. But, you think, what if I can make a small group? What if I try for a lesser goal, such as don't lose by more than 90 points? Your opponent has a 9 stone handicap because he makes more mistakes than you do. As the game progresses, those mistakes add up. You set your goal higher - losing by only 50 points; losing by only 10 points. The changing goal permits you to discriminate in a field which would otherwise look like a dark, desolate, win-less landscape. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Don Dailey dailey@gmail.com To: computer-go computer-go@computer-go.org Sent: Wednesday, August 12, 2009 1:05:36 PM Subject: Re: [computer-go] Dynamic komi at high handicaps Ok, I misunderstood his testing procedure. What he is doing is far more scientific than what I thought he was doing. There has got to be something better than this. What we need is a way to make the playouts more meaningful but not by artificially reducing our actual objective which is to win. For the high handicap games, shouldn't the goal be to maximize the score? Instead of adjusting komi why not just change the goal to win as much of the board as possible?This would be far more honest and reliable I would think and the program would not be forced to constantly waste effort on constantly changing goals. - Don On Wed, Aug 12, 2009 at 3:33 PM, Brian Sheppard sheppar...@aol.com wrote: The small samples is probably the least of the problems with this. Do you actually believe that you can play games against it and not be subjective in your observations or how you play against it? These are computer-vs-computer games. Ingo is manually transferring moves between two computer opponents. The result does support Ingo's belief that dynamic Komi will help programs play high handicap games. Due to small sample size it isn't very strong evidence. But maybe it is enough to induce a programmer who actually plays in such games to create a more exhaustive test. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Dynamic komi at high handicaps
Some algorithms are special-purpose by nature. What I sketched is an approximation of my understanding of how strong players defeat weaker players with large handicaps. When Myungwan Kim faced off against MFG a few days ago, with a 7 stone handicap, he had to come up with a strategy which would ultimately win a theoretically unwinnable game. When two pros face off, and one has a 7 stone handicap, the expectation is that the one with the handicap will not merely win, but win by 70 points. A pro with such a large handicap would be satisfied with nothing less. The Nihon Ki'in has published a book of pro-pro handicap games, where black exploits the full power of the handicap stones to give white a very thorough drubbing. David Fotland might have some insights into how MFG viewed that game. Perhaps MFG thought it was so far ahead that it was indifferent about the various opening moves. Who cares if the win rate is 99.9998 or 99.7? But there are differences, which weaker players use to hang on to as much of their advantage as possible, and stronger players use to wear down that advantage. It becomes a war of attrition - whoever runs out of troops or ammo first loses the war. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Don Dailey dailey@gmail.com To: computer-go computer-go@computer-go.org Sent: Wednesday, August 12, 2009 2:11:58 PM Subject: Re: [computer-go] Dynamic komi at high handicaps The problem with MCTS programs is that they like to consolidate. You set the komi and thereby give them a goal and they very quickly make moves which commit to that specific goal. Commiting to less than you need to actually win will often involve sacrificing chances to win.Sometime it won't, but you cannot have a scalable algorithm which is this arbitrary. However, if the handicap is too high, the program thinks every line is a loss and it plays randomly. That's why we even consider doing this. Dynamically changing komi could be of some benefit in that situation if there is no alternative reasonable strategy, but it does not address the real problem - which is what I call the committal consolidation problem. You are giving the program an arbitrary short term goal which may, or may not be compatible with the long term goal of winning the game. Whether it's compatible or not is based on your own credulity - not anything predictible or that you can scale. And as the base program gets stronger this aspect of the program becomes more and more of a wart. If this can be made to work in the short term, it should be considered a temporary hack which should be fixed as soon as possible. We have to think about this anyway sooner or later because if programs continue to develop and the predictive ability of the playouts and tree search gets several hundred ELO better, these programs may start to see more and more positions as either dead won or dead lost. I'm sure we will want some kind of robust mechanism for dealing with this which is better at estimating chances that the opponent will go wrong as opposed to doing something that is a random benefit or hindrance. - Don 2009/8/12 terry mcintyre terrymcint...@yahoo.com Ingo suggested something interesting - instead of changing the komi according to the move number, or some other fixed schedule, it varies according to the estimated winrate. It also, implicitly, depends on one's guess of the ability of the opponent. An interesting test would be to take an opponent known to be weaker, offer it a handicap, and tweak the dynamic komi per Ingo's suggestion. At what handicap does the ratio balance at 50:50? Can the number of handicap stones be increased with such an adaptive algorithm? Even better, play against a stronger opponent; can one increase the win rate versus strong opponents? The usual range of computer opponents is fairly narrow. None approach high-dan levels on 19x19 boards - yet. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Brian Sheppard sheppar...@aol.com To: computer-go@computer-go.org Sent: Wednesday, August 12, 2009 12:33:13 PM Subject: [computer-go] Dynamic komi at high handicaps The small samples is probably the least of the problems with this. Do you actually believe that you can play games against it and not be subjective in your observations or how you play against it? These are computer-vs-computer games. Ingo is manually transferring moves between two computer opponents. The result does support Ingo's belief that dynamic Komi will help programs play high handicap games. Due to small sample size it isn't very strong evidence. But maybe it is enough to induce a programmer who actually plays in such games
Re: [computer-go] Dynamic komi at high handicaps
Most experiments are done on even games; this dynamic algorithm applies particularly to handicap games.In that context, it is not an ungainly kludge, but actually reflects the assessment of evenly matched pro players - they look at the board, and see a victory of n times 10 handicap stones ( or something roughly comparable ) for black. This matters because today's programs are not even close to playing at the pro level; to win respect, they'll have to master handicap games - and to do that, they'll need to do two things. First, they'll need to model the expectation that black with a handicap _should_ win big. Second, they'll need to behave gracefully as that initial advantage is whittled down. Existing programs don't do either of those two things well. They're tuned toward even-game strategy. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Dynamic komi at high handicaps
In practical terms, the problem to solve is the reverse: how do we encourage weak programs to hang on to as much of their advantage as possible, against stronger players? In 2020, we can worry about how to beat pro players who take large handicaps against computer programs. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Don Dailey dailey@gmail.com To: computer-go computer-go@computer-go.org Sent: Wednesday, August 12, 2009 2:51:09 PM Subject: Re: [computer-go] Dynamic komi at high handicaps 2009/8/12 terry mcintyre terrymcint...@yahoo.com Most experiments are done on even games; this dynamic algorithm applies particularly to handicap games.In that context, it is not an ungainly kludge, but actually reflects the assessment of evenly matched pro players - they look at the board, and see a victory of n times 10 handicap stones ( or something roughly comparable ) for black. This matters because today's programs are not even close to playing at the pro level; to win respect, they'll have to master handicap games - and to do that, they'll need to do two things. First, they'll need to model the expectation that black with a handicap _should_ win big. Second, they'll need to behave gracefully as that initial advantage is whittled down. I disagree. I think strong players have a sense of what kind of mistakes to expect, and try to provoke those mistakes. Dynamic komi does not model that. It also does the opposite of making the program play provocatively, which I believe is necessary to beat a weaker player with a large handicap against you. Instead of making it fight, it encourages the program to be content with less. How does this model strong handicap players? - Don Existing programs don't do either of those two things well. They're tuned toward even-game strategy. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Dynamic komi at high handicaps
As for how to beat weaker players ... the strong players whom I have observed make strong, stable positions; they wait for the weaker player to make mistakes. The stronger player will leave things unresolved for longer, knowing that there will be time to extend in one direction or another later in the game. They'll include some of the more interesting, obscure joseki, which the weaker player will not grok appropriately. I have seen players who make unsound trick plays, but these are the kyu players; dan-level players know that trick plays can become costly mistakes. They'll use them for teaching purposes, not to win - but that's a different kind of game entirely. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Congratulations to Aya!
Nick, Many thanks for organizing this tournament! Did intend to reverse simplebot and :weakbot50k in one of the duplicate simplebot descriptions? Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Nick Wedd n...@maproom.co.uk To: computer-go computer-go@computer-go.org Sent: Monday, August 10, 2009 8:21:59 AM Subject: [computer-go] Congratulations to Aya! Congratulations to Aya, winner of yesterday's KGS bot tournament. My report is now at http://www.weddslist.com/kgs/past/50/index.html As always, I will welcome comments and corrections. But I am about to leave for a short holiday, so I won't respond to them for a few days. Nick -- Nick Weddn...@maproom.co.uk ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] The AGA e-journal reports Man vs Machine Rematch
KIM PREVAILS AGAIN IN MAN VS MACHINE REMATCH: The Man vs Machine rematch Friday afternoon was anti-climactic, with Myeong-Wan Kim 8P (l) handily defeating Many Faces of Go, playing with a 7-stone handicap and running a 32-core processor. MoGo defeated Kim last year on 9 stones with an 800-core processor. Kim beat Mogo – playing with 7 stones on a smaller processor -- last fall at the Cotsen Open, narrowly defeating it at the very end. “Many Faces was very different,” Kim told the audience after the game. “It behaved more like a human, while MoGo was pure computer and very unpredictable. It was easier to play Many Faces -- though it may be the stronger program -- because I could predict what it was going to do. Many Faces made better shape, but MoGo had better reading. I’d really like to see both programs play each other and see what happens.” Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] RAVE problems
Perhaps the context attached to RAVE needs to be more subtle than a static 3x3 pattern - tactical and efficiency considerations may apply - a move may be good when it defends or kills a group, but bad if it has no effect upon the status - it may be wasted in such cases. Terry McIntyre terrymcint...@yahoo.com ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Myungwan Kim 8P versus Many Faces of Go
Friday the 7th. You may check ManyFaces1 on KGS -- this is the program which will be playing - it is using 8 cores now - may be using more cores by Friday. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Ingo Althöfer 3-hirn-ver...@gmx.de To: computer-go@computer-go.org Sent: Thursday, August 6, 2009 12:48:53 AM Subject: [computer-go] Re: Myungwan Kim 8P versus Many Faces of Go Terry McI announced: On Friday, August 8th, at 3 PM Eastern Daylight Time, Myungwan Kim 8P will play against Many Faces of Go. One question, do you mean Friday, August 7th, 2009 or Saturday, August 8th, 2009 or another year ;-) Thanks for informing us. Cheers, Ingo. -- Neu: GMX Doppel-FLAT mit Internet-Flatrate + Telefon-Flatrate für nur 19,99 Euro/mtl.!* http://portal.gmx.net/de/go/dsl02 ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] Myungwan Kim 8P versus Many Faces of Go
On Friday, August 8th, at 3 PM Eastern Daylight Time, Myungwan Kim 8P will play against Many Faces of Go. Exact details as to the handicap and the size of the cluster are not yet established. This game will be played on KGS. It will played before an audience at the US Go Congress in Fairfax, Virginia. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] CiteULike
I can't speak to that question, but the group was founded by Urban Hafner, and is still owned by him. The last post I have seen by Urban Hafner was July 15, so he's probably still using that email account. Urban, are you there? Thanks! Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Peter Drake dr...@lclark.edu To: Computer Go computer-go@computer-go.org Sent: Friday, July 24, 2009 10:31:43 AM Subject: [computer-go] CiteULike There is a CiteULike group dedicated to computer Go: http://www.citeulike.org/group/5884/library No new articles have been posted since May. I tried to join a month ago to post an article, but there has been no response: http://www.citeulike.org/groupfunc/5884/home Is this group still active? Thanks, Peter Drake http://www.lclark.edu/~drake/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] demo with pro at Go Congress in Fairfax
I'm trying to set up a demo game between Myungwan Kim and Mogo at the Go Congress in Fairfax, VA Who should I speak with on the Mogo team? Will you be available? The Congress is from Aug 1-8. What times look good for you? Thanks! Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] demo with pro at Go Congress in Fairfax
I'd be happy to receive multiple offers; speak up! Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Peter Drake dr...@lclark.edu To: computer-go computer-go@computer-go.org Sent: Friday, July 24, 2009 3:37:16 PM Subject: Re: [computer-go] demo with pro at Go Congress in Fairfax Is MoGo still the best? Aren't Zen and ManyFaces doing better these days? (Perhaps the real question is who has access to a supercomputer...) On Jul 24, 2009, at 3:29 PM, terry mcintyre wrote: I'm trying to set up a demo game between Myungwan Kim and Mogo at the Go Congress in Fairfax, VA Who should I speak with on the Mogo team? Will you be available? The Congress is from Aug 1-8. What times look good for you? Thanks! Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ Peter Drake http://www.lclark.edu/~drake/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Dead stones at end of game
On KGS, either player may mark stones as dead. If you disagree, you toggle the state of the stones. The game ends when both players click done -- you should do this only when you are entirely satisfied with the score. I don't know how the human interface maps to the API seen by the program. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Jason House jason.james.ho...@gmail.com To: computer-go computer-go@computer-go.org Sent: Thursday, July 16, 2009 3:27:28 PM Subject: Re: [computer-go] Dead stones at end of game IIRC, the user can do whatever they want in a free game. Only rated games require the bot to agree with the scoring Sent from my iPhone On Jul 16, 2009, at 6:18 PM, Peter Drake dr...@lclark.edu wrote: I was looking at this game that Orego played against a human on KGS recently: Orego-Zanarkand.sgf I note that Orego's dead stones are marked as dead, but Zanarkand's are not. Does KgsGtp defer to the human when there are disputes about dead stones? Is that the most likely explanation? (What if there is a dispute between programs?) Orego loses even if all of the dead stones are removed, but I'm a bit dismayed that Orego passed. (Zanarkand passed first.) I believe Orego reasoned, If I pass, the game ends, and if all stones on the board are alive, I win! I'll have to look into this... Peter Drake http://www.lclark.edu/~drake/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Dynamic komi in commercial programs
Maybe we should go back to the question which dynamic komi is an attempt to solve: how to obtain better discrimination when every move seems to be clustered near I am so freaking dead or I am so far ahead, as the case may be. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Stefan Kaitschick stefan.kaitsch...@hamburg.de To: computer-go computer-go@computer-go.org Sent: Tuesday, July 14, 2009 3:17:38 PM Subject: Re: [computer-go] Re: Dynamic komi in commercial programs Dynamic komi in a sense means that the bot is deluding itself on purpose. Obviously this is dangerous medicine, a kind of magic mushroom. So what could be worse than a deluded bot? I say, letting a monkey play could be worse. And monkeys' play is what you get from an mc bot when all possible moves come back with indistinguishably wonderful or terrible win rates. Adding a wishful (or pessimistic) komi will distort reality, but will help create bigger win rate differences between moves. It should be possible to assign costs to both dynamic komi and to insufficiently spreading win rates between moves. My hypothesis is, that with unstable groups on the board, the win-rate spread will tend to be larger then with stable groups. So with proper balancing, the bot should refuse to take dynamic komi when he sees a chance to win outright. Stefan ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Dynamic komi in commercial programs
Is it possible to design metrics for complexity of positions? An opponent model could make use of that information; there are positions which some players will totally fail to grok. Double-digit kyu players are weak on life-and-death, ko, and seki. Some otherwise strong programs will fail to read seki properly. As players move up in rank, they read life-and-death at an earlier point. Human players, with practice, discover the weaknesses of their particular opponents. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Magnus Persson magnus.pers...@phmp.se I am open to opponent modeling such as make the playouts of black in handicap games weaker. But in this case I think real gain if any would come from making the statistics more sensitive to the qualitative difference in available moves, rather than actually modeling the opponent, by bringing the win rates closer to 50%. Although I think it would be really hard to degrade the black moves in the playouts in a realistic way. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Dynamic komi in commercial programs
That's an interesting idea - factoring in knowledge about the variability of a position. Certain parts of the board are going to be stable with alternating play - you attack, I defend, the position remains stable. Other parts of the board are less well-defined. On the 9x9 board, conflicts easily spill over; everything is inter-connected until the end-game. On the 19x19 board, it's possible to establish stable groups, and the action usually happens on the borders. Factor in seki, ko fights, etc. Simply varying komi as some pre-ordained function of move number is unlikely to have enough granularity to cope with the structure of a particular game. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Don Dailey dailey@gmail.com To: computer-go computer-go@computer-go.org Sent: Sunday, July 12, 2009 3:40:10 PM Subject: Re: [computer-go] Re: Dynamic komi in commercial programs On Sun, Jul 12, 2009 at 1:22 PM, Christian Nentwich christian.nentw...@gmail.com wrote: Don, others, are there publications about this? If people have tried it out, are there any threads on this list that somebody remembers where results are posted? I have not been able to find any. It would be interesting to see. I think I just mentioned that there is probably not much on this except in the archive.And even then it's probably not very well documented. I did try this myself but I don't have any data to show what I did.What I remember is that it's incredibly tricky - how do you actually know when and how much to adjust? If the score starts getting really low or really high, do you restart the search with a new komi?If you restart then you have wasted effort. I tried 2 different thing. One of them involved using the total points won in some kind of hybrid approach and the other involved changing the komi during the game. Using JUST the total points won is a drastic weakening of the program and it's surprising how much. I tried factoring in a percentage of total points won and other things.After some time I gave up - it seemed like I was taking something that worked well and trying to make it better by factoring in something that sucked. It was like trying to make it play better by putting something in on purpose that I knew makes it play worse. The dynamic komi adjustment, from my recollection was more promising, but still played worse. The only way to make this work is if you know in advance what kind of position you really have.If you KNOW that you can pick off a small group without risk, then it probably would work just fine.But just increasing komi for no reason except that you are winning is not good enough. For instance if you KNOW there is a seki issue, then you should probably do it. But just doing it because there MIGHT be a seki issue every 50 games that actually matters is not good enough. You could call this a chicken and egg problem.You can of course easily construct positions that will illustrate how wonderful the idea is, and it will probably work great in those positions.Seki positions are always given as to why this will help - but not every game has a game critical seki. But I'm pretty convinced you cannot generalize the idea. You would have to do some kind of pre-analsysis to figure out what needs to be done, and by then you may already know what to do anyway and you have a more convential program. - Don Christian 2009/7/12 Don Dailey dailey@gmail.com: On Sun, Jul 12, 2009 at 8:59 AM, Benjamin Teuber benjamin.teu...@web.de wrote: You just hit the nail on the head. Dynamic komi does not encourage a program to overplay the position. Since you are starting from a losing position you HAVE to overplay a bit. You have to attack when it is futile. That depends on the komi - if you're behind by fourty points and set the virtual komi to 30, you play as if you'd be 10 behind, which would be agressive, but not kamikaze. This is exactly what people do, so I don't see your point. It's not up to me to prove anything. It's up to you. Several of us have tried variations of this idea of dynamic komi adjustment, which seems like a very good premise. This SHOULD help the play.But the fact of the matter is that none of us (so far) has made it work. If the observations do not fit the premise, at some point we should actually scrutinize the premise - even if the premise seems logical to us. I think the ones who still cling to this idea have not actually tried implementing it.Have you tried?If you have, why are still talking about it and not showing us something? - Don Benjamin ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer
Re: [computer-go] Dynamic komi in commercial programs
The go-playing literature offers a bit of advice: when ahead, make moves which simplify the game and preserve your advantage. When behind, take some risks to grab more than you are entitled to - but not too many. Computer programs seem bizarre in this regard, they tend to play quite unsatisfactory moves when behind. It would be more attractive to see the computer preserve its advantage, the better to spring when one's opponent lapses. A complex seki was recently posted. Magnus explained that his program does not understand the seki per se, but finds the correct move through several intricately-meshed rules which prune bad moves. He's not entirely sure of the correctness of those rules - that is, whether they apply to all cases, or merely most cases. At the single-digit-kyu level, inducing sekis is not unusual; it is basic for dan-level players. Some high-dan players prefer to give a large negative komi instead of handicap stones; the game mechanics are closer to those of an even game. The stronger player gains incrementally with every suboptimal move by the weaker; eventually, the advantage of the negative komi dissipates. When can we train our programs, instructing them don't do that, it will only hurt you? ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Scoring - step function or sigmoid function?
To properly test any method of playing with a handicap, today's programs will need to play against much stronger opponents. Self-play, or play against other roughly-equal programs, won't test the ability to eke out a win against a professional go player. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Prediction
--- On Wed, 7/8/09, Michael Williams michaelwilliam...@gmail.com wrote: From: Michael Williams michaelwilliam...@gmail.com Prediction: First, developers and algorithm gurus will expend huge amounts of effort to parallelize code to take advantage of multi-core chips. Then, hardware engineers and physics gurus will give us light-based CPUs and orders of magnitude improvement in single-core performance. Quite all right! light-based CPUs will come in multi-core versions too! ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Really basic question
megasnippage of Don's post: Adding an additional order of magnitude more time to the search [ in Rybka] is not going to change the basic misconception if the evaluation just doesn't understand the position. [ Don suggests that this applies even more so to Go ] Amen! We've covered variants of this theme a few times. I believe that when the playout component knows as much about life-and-death, corner plays, nakade, running fights, semeai, and seki as a dan-level player, the power of the tree search will leverage that knowledge far better than at present. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Experimentation
Digesting Don's remarks, it seems that a reasonable method would start with equal numbers of simulations. It could then proceed to try various optimizations, and compare algorithms which use equal time. It makes perfect sense for the ultimate goal to be better performance using the same time or less, but it might be easier to progress stepwise - first tweak the top-level design, then tweak the performance - in order to separate out the different inputs to the experiment. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Hash tables
Considering that memory keeps getting cheaper, would it make sense to dynamically choose how much space to use? Nowadays most new computer purchasers start with 2 GB, and go up from there. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: David Fotland fotl...@smart-games.com To: computer-go computer-go@computer-go.org Sent: Sunday, July 5, 2009 9:05:45 PM Subject: RE: [computer-go] Hash tables The hash table contains a linked list of nodes with the same hash index. Your description is pretty close, but I don't remember the exact details. Yes, I keep around some nodes for while, but eventually old nodes go into the past and can be recovered. I actually have fewer total nodes than you do. The commercial version allocates 30K nodes per CPU core. The version in the world championship had much more, but the commercial version can't be that greedy for memory. David I give up when there are no nodes that area available to be overwritten. I'm still a little confused. First, does the hash table contains pointers into a node pool, or do you use the node pool as the hash table? Second, how and when do you determine which nodes (if any) are available for overwriting, without doing some sort of traversal? Is the following a correct summary of what you do when it's time to create a new node? Go to the one node that would be used for this Zobrist hash. If the same hash is stored there, use the existing node. If not, either overwrite this node (if this node is available for overwriting) or not create a new node (otherwise). Also, what exactly is the criterion for overwriting? You said nodes that have few visits or are old. Is this just (visits visitThreshold) || (depthFromBeginningOfGame currentGameTurn)? Doesn't depthFromBeginningOfGame cause you to keep around nodes that are outside the still-relevant branch of the tree (i.e., the branch descending from the current root), almost all of which are irrelevant? If the search is long enough, there are no nodes that can be recovered, and the UCT tree stops growing. I keep searching when there are no reusable nodes. ...because this improves the quality of information in the nodes you were able to create. That makes sense. Thanks, Peter Drake http://www.lclark.edu/~drake/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Fuego or Fuego?
From merriam webster entry for terra del fuego, it can be foo-ay-go or fway-go It's a Spanish word -- have to ask some Spanish speakers their opinions. http://forvo.com/word/fuego/ -- to my ear, it sounds like foo eh go -- three distinct syllables. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: Michael Williams michaelwilliam...@gmail.com To: computer-go computer-go@computer-go.org Sent: Friday, June 19, 2009 10:58:14 AM Subject: [computer-go] Fuego or Fuego? Is it pronounced few-go or fway-go? ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] MCTS, 19x19, hitting a wall?
From: Don Dailey dailey@gmail.com My basic observation is that over the several year period I have been in this forum, I have detected a huge amount of resistance to the idea that hardware could have anything to do with computer go strength, despite the fact that it keeps proving to be so. The resistance is strong enough that we have to explain it way when it happens, by saying things like we have hit a wall and it won't happen any more thank goodness. You overrstate the resistance - it's not that anybody is saying hardware is irrelevant. In fact, did we not have a recent discussion over the merits of two different CPU variations? We've seen a fair number of multi-processor entrants at competitions, besides. The questions ishow much does hardware matter? So far, we have one data point to work with: David Fotland's excellent Many Faces of Go is about one stone stronger when it uses 32 cores instead of 2. That's nice to have, but if we extrapolate, a factor of 16 is 3 doublings or about 4.5 years, in terms of Moore's Law. It will only take 9*4.5, roughly 40 years, to reach pro-level play. We don't have data from Mogo yet, but I wonder if they are seeing 2-3 stones improvement for their 3200-node version? The less patient among us may wish to seek algorithmic improvements to bridge the gap a bit sooner. Got to be some reason for bright programmers and mathematicians to work on the problen, after all; otherwise we could just wait 40 years for Intel and AMD to deliver 32,768 cores on a single chip - or will it be a silicon wafer? In other fields, algorithmic improvements have led multiple orders of magnitude improvement in running time. Humans manage to complete 30-minute games on a 19x19 board, so we do have evidence that the game can be played well at such a speedy pace. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] MCTS, 19x19, hitting a wall?
Regarding Moore's Law, I'd love to hear the Mogo team's perspective on this; they have probably had more opportunity to test their algorithms extensively on big-n-count computers than any of us. If I recall correctly, the Huygens supercomputer uses 800 to 3200 cores -- one to four hundred times the equivalent of an 8 core machine, which might be considered a reasonable investment for a well-heeled enthusiast. How much stronger is the 800 or 3200-core version of Mogo, compared to the 4 or 8 core version, for the same time limits, on 19x19 Go? David Fotland has done quite a bit with a 32-core machine, I believe. How much stronger is MFG on 32 cores versus 4, for the same time limits, on 19x19 Go? Hopefully, how much stronger would be tested with something other than self-play against a weaker program - play on KGS, or CGOS, or something more diverse than a weaker clone of oneself. Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] US Go Congress
I can volunteer to organize the computer versus pro demonstration. Myung-Wan Kim lives in Los Angeles and I can approach him; he played against Mogo last year. Will Mogo be available? Mogo team, do you feel that Mogo has improved since the previous demonstration? Which is the strongest computer go program nowadays? Terry McIntyre terrymcint...@yahoo.com “We hang the petty thieves and appoint the great ones to public office.” -- Aesop From: David Doshay ddos...@mac.com To: computer-go computer-go@computer-go.org Sent: Tuesday, June 9, 2009 10:56:30 AM Subject: Re: [computer-go] US Go Congress Because of my health problems I will not be able to attend this year either, so neither of the two people who ran last year's event in Portland will be able to do it this year. Any other volunteers? It would be nice if this became a regular event again. Cheers, David On 9, Jun 2009, at 9:27 AM, Peter Drake wrote: Due to other commitments, I will NOT be attending the US Go Congress in Fairfax, Virginia, August 1-9. As a result, if there is to be any computer Go event there (e.g., computer-computer tournament, computer-professional match), someone else will have to organize it. Peter Drake http://www.lclark.edu/~drake/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] bots and handicaps (Re: New CGOS)
Pro ranks are assumed to be about 1/3 of a stone; the one stone per rank formula applies to amateur ranks. I have watched a pro 8p regularly give three stones to a 6 dan amateur. A weaker pro might give the same player 2 stones. Some ( including myself in the past ) have argued that they can easily beat a person who is nine ranks higher with a nine stone handicap. I have done this often enough that I believed it. However, after losing a fair number of such 9-stone games, I conclude that many people slack off, assuming that their opponent is really inept; if the weaker player can keep most of his groups alive, and pressure white, he will win. When white aggressively exploits weak groups, the weaker player's positions collapse. A dan-level player has an understanding of life and death which seems almost magical to a weaker player. When that superior knowledge is exploited, the weaker player crumbles. Last week, I played a series of 9-stone games. After losing three in a row, my opponent thanked me for giving him a serious challenge. I think many players do not rise to that challenge; they don't apply their full strength against kyu-level players. Until computer programs rise to the level of even play against pros, human-computer matches will be handicap games. It makes sense to develop the ability to play handicap games well. It would be sad if a program with a seven stone handicap frittered away its advantage instead of hoarding it jealously. Terry McIntyre terrymcint...@yahoo.com Any system of entrusting the government to judge and correct its own abuses is the same as appointing the accused criminal as his own judge and jury: don't expect many convictions. -- Allen Thornton, Laws of the Jungle ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] bots and handicaps (Re: New CGOS)
I was referring to matches against pro players. It's going to be a while before a computer can win even games against pros, therefore we must assume that any such matches will involve the program taking a handicap. My personal preference is the strongest possible opponent. When reviewing games that I have won against computer programs, I find that tweaking just one computer move would often destroy my position; hence, I was getting false feedback, believing my position to be superior when in fact it was terribly weak. Play against devastatingly strong opponents (from my point of view) has motivated me to discover (and hopefully repair) weaknesses in my reading skills. Playing against opponents of my level only encourages me to be a little trickier - to push problems beyond the horizon of my opponent's skills (and often my own). Terry McIntyre terrymcint...@yahoo.com Any system of entrusting the government to judge and correct its own abuses is the same as appointing the accused criminal as his own judge and jury: don't expect many convictions. -- Allen Thornton, Laws of the Jungle From: David Fotland fotl...@smart-games.com To: computer-go computer-go@computer-go.org Sent: Sunday, June 7, 2009 11:06:37 AM Subject: RE: [computer-go] bots and handicaps (Re: New CGOS) I can’t really agree with this statement. My customers tell me they would much rather play a challenging even game against an opponent of their level, than a challenging handicap game against a much stronger or much weaker opponent. This is why version 12 of Many Faces has levels that are calibrated to be about 3 stones apart, so there is always a level that does not require a handicap, unless you are weaker than 20 kyu or stronger than 1 dan. Until computer programs rise to the level of even play against pros, human-computer matches will be handicap games. It makes sense to develop the ability to play handicap games well. It would be sad if a program with a seven stone handicap frittered away its advantage instead of hoarding it jealously. Terry McIntyre terrymcint...@yahoo.com ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] New CGOS
The purpose of a handicap games is to allow a 50% chance of either contestant winning. If one program loses 100% of games against another, it would take a vast improvement to advance to 90% or 80%. If the same two programs have an appropriate handicap, and a base of 50% odds, it should be easier to see the beneficial impact of various changes. Contrast my winrate against a motley assortment of opponents, which changes month-to-month, is 3% higher than yours with my program can give yours two stones, and still win 50% of the games. Programs do not care, but their human designers might have an incentive to find a way to leapfrog over their opponents. Terry McIntyre terrymcint...@yahoo.com Any system of entrusting the government to judge and correct its own abuses is the same as appointing the accused criminal as his own judge and jury: don't expect many convictions. -- Allen Thornton, Laws of the Jungle From: Christoph Birk b...@ociw.edu To: computer-go computer-go@computer-go.org Sent: Friday, June 5, 2009 2:59:07 PM Subject: Re: [computer-go] New CGOS On Fri, 5 Jun 2009, Don Dailey wrote: Handicap games opens a can of worms. The last time we discussed it, it was difficult to get any kind of reasonable agreement on how to do it. Handicap games are for humans ... they get frustrated losing over and over. Computers have no problems with that. I agree with Don, adding a handicap server is an unnecessary complication. Christoph ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Implications of a CPU vs Memory trend on MCTS
I concur with Don; for the early moves, this is likely to be helpful. On a 19x19 board, the first ten or fifteen moves of a pro game often follow fairly well-known patterns, but it's not enough to simply memorize the patterns; there is deep knowledge which explains why one 3,4 point is better than the other, or why a particular joseki matches the overall position, and another is a failure. Building up a tree over time which knows something about the various choices might be helpful. Terry McIntyre terrymcint...@yahoo.com On general principles, when we are looking for a solution of a social problem, we must expect to reach conclusions quite opposed to the usual opinions on the subject; otherwise it would be no problem. We must expect to have to attack, not what is commonly regarded as objectionable, but what is commonly regarded as entirely proper and normal. – John Beverley Robinson, 1897 ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Implications of a CPU vs Memory trend on MCTS
Memory-aware algorithms take advantage of the varying access characteristics. Long, long ago, computer memory was actually a rotating drum; each instruction chained to the next location; it was worth a lot of effort to place the instructions in such a manner that they'd be where you need them when they were needed. Not every bit of information needs to be available Right Now; if we map access needs to the access capabilities, an SSD can be a great way to extend RAM cheaply. This is all the more true when newer flavors of SSD become available in the next few years. Terry McIntyre terrymcint...@yahoo.com On general principles, when we are looking for a solution of a social problem, we must expect to reach conclusions quite opposed to the usual opinions on the subject; otherwise it would be no problem. We must expect to have to attack, not what is commonly regarded as objectionable, but what is commonly regarded as entirely proper and normal. – John Beverley Robinson, 1897 From: Michael Williams michaelwilliam...@gmail.com To: computer-go computer-go@computer-go.org Sent: Tuesday, May 12, 2009 9:48:19 AM Subject: Re: [computer-go] Implications of a CPU vs Memory trend on MCTS It depends on how you use it and how much you pay for it. If you get a high-end Intel SSD, you can treat it however you like. But I can't afford that. I got a cheap SSD and so I had shape my algorithm around which kind of disk operations it likes and which ones it doesn't. steve uurtamo wrote: is the ssd fast enough to be practical? s. On Tue, May 12, 2009 at 12:41 PM, Michael Williams michaelwilliam...@gmail.com wrote: Don Dailey wrote: On Tue, May 12, 2009 at 12:16 PM, Michael Williams michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com wrote: I have a trick ;) I am currently creating MCTS trees of over a billion nodes on my 4GB machine. Ok, I'll bite.What is your solution? I use an SSD. There are many details, of course. But it's still in the works and I'm still making lots of changes and adjustments. I seem to be able to solve (there are lots of definitions) 6x6 Go in that when I use a komi of 3.5, it is unable to find a winning line for white and when I use 4.5, it is unable to find a winning line for black. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Implications of a CPU vs Memory trend on MCTS
Are we approaching a point where it would be practical to precompute the opening tree to some depth, cache the results on SSD, and incrementally improve that knowledge based upon subsequent games? Terry McIntyre terrymcint...@yahoo.com On general principles, when we are looking for a solution of a social problem, we must expect to reach conclusions quite opposed to the usual opinions on the subject; otherwise it would be no problem. We must expect to have to attack, not what is commonly regarded as objectionable, but what is commonly regarded as entirely proper and normal. – John Beverley Robinson, 1897 From: Michael Williams michaelwilliam...@gmail.com To: computer-go computer-go@computer-go.org Sent: Tuesday, May 12, 2009 10:18:28 AM Subject: Re: [computer-go] Implications of a CPU vs Memory trend on MCTS In my system, I can retrieve the children of any node at a rate of about 100k nodes/sec. And I can save nodes at a rate of over 1M nodes/sec (this is much faster because in my implementation, the operation is sequential on disk). Those numbers are from 6x6 testing. Don Dailey wrote: This is probably a good solution. I don't believe the memory has to be very fast at all because even with light playouts you are doing a LOT of computation between memory accesses. All of this must be tested of course. In fact I was considering if disk memory could not be utilized as a kind of cache. The secret would be to store complete trees in disk memory, trees that are not likely to be utilized but can be utilized in a pinch. The tree store and retrieved must outweigh by a large factor the amount of time spent creating the tree in the first place in order for this to pay off. My guess is that this is impractical, but it's fun to think about how it might be done. I'm not sure how to do it without having a caching nightmare. - Don On Tue, May 12, 2009 at 12:41 PM, Michael Williams michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com wrote: Don Dailey wrote: On Tue, May 12, 2009 at 12:16 PM, Michael Williams michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com wrote: I have a trick ;) I am currently creating MCTS trees of over a billion nodes on my 4GB machine. Ok, I'll bite.What is your solution? I use an SSD. There are many details, of course. But it's still in the works and I'm still making lots of changes and adjustments. I seem to be able to solve (there are lots of definitions) 6x6 Go in that when I use a komi of 3.5, it is unable to find a winning line for white and when I use 4.5, it is unable to find a winning line for black. ___ computer-go mailing list computer-go@computer-go.org mailto:computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Implications of a CPU vs Memory trend on MCTS
How long has it been pondering? Terry McIntyre terrymcint...@yahoo.com On general principles, when we are looking for a solution of a social problem, we must expect to reach conclusions quite opposed to the usual opinions on the subject; otherwise it would be no problem. We must expect to have to attack, not what is commonly regarded as objectionable, but what is commonly regarded as entirely proper and normal. – John Beverley Robinson, 1897 From: Michael Williams michaelwilliam...@gmail.com To: computer-go computer-go@computer-go.org Sent: Tuesday, May 12, 2009 1:09:41 PM Subject: Re: [computer-go] Implications of a CPU vs Memory trend on MCTS That's basically what I'm doing. Except that there is no depth limit and only the parts of the tree that you need get loaded back into memory. It's not a playing engine yet so it can't build the tree as it plays games. Currently it just ponders the empty board. terry mcintyre wrote: Are we approaching a point where it would be practical to precompute the opening tree to some depth, cache the results on SSD, and incrementally improve that knowledge based upon subsequent games? Terry McIntyre terrymcint...@yahoo.com On general principles, when we are looking for a solution of a social problem, we must expect to reach conclusions quite opposed to the usual opinions on the subject; otherwise it would be no problem. We must expect to have to attack, not what is commonly regarded as objectionable, but what is commonly regarded as entirely proper and normal. – John Beverley Robinson, 1897 *From:* Michael Williams michaelwilliam...@gmail.com *To:* computer-go computer-go@computer-go.org *Sent:* Tuesday, May 12, 2009 10:18:28 AM *Subject:* Re: [computer-go] Implications of a CPU vs Memory trend on MCTS In my system, I can retrieve the children of any node at a rate of about 100k nodes/sec. And I can save nodes at a rate of over 1M nodes/sec (this is much faster because in my implementation, the operation is sequential on disk). Those numbers are from 6x6 testing. Don Dailey wrote: This is probably a good solution. I don't believe the memory has to be very fast at all because even with light playouts you are doing a LOT of computation between memory accesses. All of this must be tested of course. In fact I was considering if disk memory could not be utilized as a kind of cache. The secret would be to store complete trees in disk memory, trees that are not likely to be utilized but can be utilized in a pinch. The tree store and retrieved must outweigh by a large factor the amount of time spent creating the tree in the first place in order for this to pay off. My guess is that this is impractical, but it's fun to think about how it might be done. I'm not sure how to do it without having a caching nightmare. - Don On Tue, May 12, 2009 at 12:41 PM, Michael Williams michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com wrote: Don Dailey wrote: On Tue, May 12, 2009 at 12:16 PM, Michael Williams michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com mailto:michaelwilliam...@gmail.com wrote: I have a trick ;) I am currently creating MCTS trees of over a billion nodes on my 4GB machine. Ok, I'll bite.What is your solution? I use an SSD. There are many details, of course. But it's still in the works and I'm still making lots of changes and adjustments. I seem to be able to solve (there are lots of definitions) 6x6 Go in that when I use a komi of 3.5, it is unable to find a winning line for white and when I use 4.5, it is unable to find a winning line for black. ___ computer-go mailing list computer-go@computer-go.org mailto:computer-go@computer-go.org mailto:computer-go@computer-go.org mailto:computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org mailto:computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org mailto:computer-go@computer-go.org http://www.computer-go.org
Re: [computer-go] Re: Implications of a CPU vs Memory trend on MCTS
In the opening, among reasonably clueful players, the branching factor is much closer to 10 than to 361. Terry McIntyre terrymcint...@yahoo.com On general principles, when we are looking for a solution of a social problem, we must expect to reach conclusions quite opposed to the usual opinions on the subject; otherwise it would be no problem. We must expect to have to attack, not what is commonly regarded as objectionable, but what is commonly regarded as entirely proper and normal. – John Beverley Robinson, 1897 From: Michael Williams michaelwilliam...@gmail.com Subject: Re: [computer-go] Re: Implications of a CPU vs Memory trend on MCTS You have made the assumption that the move that your opponent selected was on average explored equally as much as all of the other moves. That seems a bit pessimistic. One would expect that the opponent selected a strong move and one would also expect that your tree explored that strong move more than it did other moves. I'm not saying keeping the tree is a huge benefit. I'm just saying that I don't think your 99% number is fair. Dave Dyer wrote: At 02:13 PM 5/12/2009, Michael Williams wrote: Where does your 99% figure come from? 1/361 1% by endgame there are still easily 100 empty spaces on the board. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Implications of a CPU vs Memory trend on MCTS
It's possible for the tree to become too narrow. On a 9x9 board, you might be able to say that there are only one or two playable moves, but on 19x19, I doubt that any pro would claim that the options are that narrow, even accounting for symmetry, It's common to hear that some pros play A, some B, some C or D in this situation. Moderately strong amateurs play one of these other options, which are mistakes because ... An opening book could benefit from knowing how to respond to the options considered by both pros and strong amateurs. As for weaker players like me, we tend to be somewhat more creative, you'll just have to work it out on the fly. I think an efficient opening book would be organized on principles similar to huffman encoding: it would devote space to high-probability branches, and less to the weird stuff - but enough memory might be retained to eventually observe Gee, opponent X does this a lot, and I have discovered a good refutation Y. Terry McIntyre terrymcint...@yahoo.com On general principles, when we are looking for a solution of a social problem, we must expect to reach conclusions quite opposed to the usual opinions on the subject; otherwise it would be no problem. We must expect to have to attack, not what is commonly regarded as objectionable, but what is commonly regarded as entirely proper and normal. But as Don says, this needs to be integrated with the basic search algorithm to scale well. I recently tried a few games against Leela, where the first 8 opening plays were predetermined ( a mini chinese opening ). This is not the usual style of Leela. I find that I can win either side of the same position. When Leela and I start with an empty board, I have a harder time of it; Leela's style is not mine. – John Beverley Robinson, 1897 From: Don Dailey dailey@gmail.com To: computer-go computer-go@computer-go.org Sent: Tuesday, May 12, 2009 3:14:55 PM Subject: Re: [computer-go] Re: Implications of a CPU vs Memory trend on MCTS On Tue, May 12, 2009 at 6:05 PM, Don Dailey dailey@gmail.com wrote: And for MCTS it is much lower than 10. 2009/5/12 terry mcintyre terrymcint...@yahoo.com In the opening, among reasonably clueful players, the branching factor is much closer to 10 than to 361. I assume Dave Dyer does not understand alpha beta pruning either, or he would not assume the branching factor is 361.But the pruning we are doing is far more severe than even alpha/beta pruning.(In a theoretical sense this is not true because a proper MCTS eventually would have to explore the tree in alpha/beta fashion to provide a proof.)In practical MC programs the effective BF is extremely low. - Don Terry McIntyre terrymcint...@yahoo.com On general principles, when we are looking for a solution of a social problem, we must expect to reach conclusions quite opposed to the usual opinions on the subject; otherwise it would be no problem. We must expect to have to attack, not what is commonly regarded as objectionable, but what is commonly regarded as entirely proper and normal. – John Beverley Robinson, 1897 From: Michael Williams michaelwilliam...@gmail.com Subject: Re: [computer-go] Re: Implications of a CPU vs Memory trend on MCTS You have made the assumption that the move that your opponent selected was on average explored equally as much as all of the other moves. That seems a bit pessimistic. One would expect that the opponent selected a strong move and one would also expect that your tree explored that strong move more than it did other moves. I'm not saying keeping the tree is a huge benefit. I'm just saying that I don't think your 99% number is fair. Dave Dyer wrote: At 02:13 PM 5/12/2009, Michael Williams wrote: Where does your 99% figure come from? 1/361 1% by endgame there are still easily 100 empty spaces on the board. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] a ladder example
I promised an example of a monte carlo program mistakenly starting a ladder; here it is. I played white; Leela had a 2 stone handicap and 45 minutes on the clock. Leela's move 32 initiates a ladder. Unfortunately for Leela, I have a ladder breaker at D16. Leela's analysis was optimistic when it initiated the ladder, but a few moves later, it became aware of the looming shadow of a great doom. There are a few large captures later in the game. The corner fight at the end had me biting my nails. Terry McIntyre terrymcint...@yahoo.com Here you can see how slightly a people needs to be governed. - Carl Schurz, immigrant, 1848. What happened since? score_me.sgf Description: Binary data ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] a ladder example
Is it practical to recognize the initiation of a ladder, and expand the nodes all the way to the end, to determine whether it works or not? More generally speaking, if a large group can be repeatedly put into atari, the outcome will usually swing the game one way or the other. One of the players pursuing a ladder has usually made a fatal error; Hugh Grant Important to know. Terry McIntyre terrymcint...@yahoo.com Here you can see how slightly a people needs to be governed. - Carl Schurz, immigrant, 1848. What happened since? From: David Fotland fotl...@smart-games.com To: computer-go computer-go@computer-go.org Sent: Saturday, May 2, 2009 11:35:36 AM Subject: RE: [computer-go] a ladder example I think all uct/mc programs will have this problem unless they add something extra to avoid it. During playouts using random moves the playouts will think that the ladder usually works. Local 3x3 patterns aren’t enough since they can’t tell the difference between ladders that work and ladders that don’t work. Some programs read ladders during playouts so they know the local result and can play correctly. Many Faces doesn’t read ladders during playouts, since I think it’s too slow, but I found a different solution to the problem. Mogo and Crazystone must some solution to this problem, but I don’t know what it is. This should only show up for long ladders, since the UCT tree part of the search will read a ladder correctly. David From:computer-go-boun...@computer-go.org [mailto:computer-go-boun...@computer-go.org] On Behalf Of terry mcintyre Sent: Saturday, May 02, 2009 9:49 AM To: computer go Subject: [computer-go] a ladder example I promised an example of a monte carlo program mistakenly starting a ladder; here it is. I played white; Leela had a 2 stone handicap and 45 minutes on the clock. Leela's move 32 initiates a ladder. Unfortunately for Leela, I have a ladder breaker at D16. Leela's analysis was optimistic when it initiated the ladder, but a few moves later, it became aware of the looming shadow of a great doom. There are a few large captures later in the game. The corner fight at the end had me biting my nails. Terry McIntyre terrymcint...@yahoo.com Here you can see how slightly a people needs to be governed. - Carl Schurz, immigrant, 1848. What happened since? ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Monte-Carlo Simulation Balancing
A fair number of amateur moves are exactly what a pro would use; this is no great surprise, since the moves are actually copied from professional games. The weaker player can blindly emulate, but does not know why a pro plays A instead of B or C; does not know how to punish slack moves. I've been taking some classes from an 8d pro. Sadly, I'm at the bottom of the class. The top players in these classes are 8d amateurs; the pro can give them 3 stones and win. When going over their games, many of their moves are quite respectable, but the pro is able to find mistakes which can be exploited with devastating effect. You can't afford to be a little bit off against a pro, but weaker players find it hard to exploit slack moves. When explaining his moves, the pro often uses very deep reading. We've all seen simple cases, where move A is advisable if a ladder works, otherwise B is recommended. The pro knows six moves in advance that he'll need to read that ladder, before the ladder is actually on the board. These are the simplest expositions I've seen; things get more complex from there. Terry McIntyre terrymcint...@yahoo.com Government is an association of men who do violence to the rest of us. - Leo Tolstoy From: steve uurtamo uurt...@gmail.com To: computer-go computer-go@computer-go.org Sent: Tuesday, April 28, 2009 5:09:20 PM Subject: Re: [computer-go] Monte-Carlo Simulation Balancing also, i'm not sure that a lot of most amateurs' moves are very good. the spectrum of bad moves is wide, it's just that it takes someone many stones stronger to severely punish small differences between good and nearly-good moves. among players of relatively similar strength, these differences will go unnoticed and unpunished. s. 2009/4/28 Don Dailey dailey@gmail.com: A simplistic model that helps explain this is golf. On a single hole, even a casual golfer has a realistic chance of out-golfing Tiger Woods. Tiger occasionally shoots a 1 over par on some hole and even weak amateurs occasionally par or even birdie a hole.It's not going to happen a lot, but it's not ridiculous either. Years ago I taught a player how to golf, and on his third time out with me, he hit a hole in one on a short par 3. If Tiger Woods had been playing with us, he would have lost that hole to this beginner. But in a 9 hole match, the odds go down enormously - for all practical purposes there is no chance. I kind of think of GO like that, even though it's a pretty simplistic model. Each move is like a hole of golf, it can be a good shot or a bad one. With GO, however, probably a LOT of your moves are just as good as the moves of a good player. But it's the ones that fall short, that kill you. Go on a big board is like 18 holes of golf compared to just 1 or 2 holes of golf. The better player is far more likely to win the 18 hole match than the 1 hole match. - Don On Tue, Apr 28, 2009 at 1:53 PM, Ivan Dubois dubois_i...@yahoo.fr wrote: I noticed that, in general, changes in the playout policy have a much bigger impact on larger boards than on smaller boards. Rémi I think rating differences are emplified on larger boards. This is easy to see if you think about it this way : Somehow a 19x19 board is like 4 9x9 boards. Let us define a new game that I would call 4-Go where instead of playing one game, you play simultenously 4 games and determine the winner by calculating the sum of the scores of the four games. Certainly rating differences would be bigger with 4-go than with go (given the same two players). This explains why rating differences are bigger on 19x19 than 9x9. Ivan ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Roadmap 2020 - using analysis mode to improve programs
I appreciate that Go programs are complex and not easy to tune. Thinking over Magnus' excellent automated method ( play many games, allow early resignation, inspect long games ), and my own experiences, I'd like to suggest an additional method: when a game ends with a large loss, determine retroactively a) how far back the program was doomed but deluded about the outcome, and b) what the correct earlier plays would have been. Tune and test with a regression suite of difficult positions. This is like troubleshooting any other large and complex program; a subtle error in one portion may only reveal itself when a perfect storm of circumstances arises - but the bug is there all the time. As Magnus and Valkyria pointed out, proper play at an earlier point in my example game would have destroyed Black's position. I don't feel so proud now, lol. At my level of play, it is distressingly common to mis-read capturing races -- it's possible that a good understanding of that topic would improve Go programs. The difficulty cannot be understated - others have indicated that Hunter's Counting Liberties and Winning Capturing Races book, valuable as it may be, misses some cases. As Hunter observes, even dan-level players sometimes make mistakes in capturing races. Programs which get semeai and seki right every time might be a few stones stronger. They'd certainly be more valuable as teaching tools. In the game above, a stronger program would have exploited my earlier weakness; this would have encouraged me to make better moves. Back to Roadmap: 2020, I'd love a status map showing groups which are certainly alive, groups which are unstable, and groups which are certainly dead ( assuming proper play ). That would be quite a feedback tool. When an approach move or throw-in threatens the status of a group, the group marker would change from green to blinking yellow. When the attack succeeds, the group marker would change to red. To be useful, this tool would have to be accurate. If not 100% accurate, it should at least give some indication of its level of confidence. Even better, especially for double-digit-kyu players, would be an exposition of why a group is live, dead, seki, unstable, etc. Terry McIntyre terrymcint...@yahoo.com Government is an association of men who do violence to the rest of us. - Leo Tolstoy ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Roadmap 2020 - using analysis mode to improve programs
I haven't got a ladder example at the moment, but here's an instance where Leela does not realize it is in terrible trouble. I ( with my 8 kyu AGA rating) know with certainty by move 223 (T5) that Black has captured a large white group. A stronger player could read this out sooner than I. This fight is too big to lose for either side; nothing else on the board matters. ( anyone? how early is this outcome pre-ordained? ) Based on the results of its analysis mode, Leela does not recognize the outcome of this semeai until the large white group in the bottom right is down to two liberties. The problem is even more stark in example2 -- similar board, black has foolishly played one of his own liberties for illustrative purposes. It is black's play, black has three liberties, white has three. Black must take away a liberty from white to win the capturing race, or make two eyes at T8. Black has only four playable moves; any other choice fails. Leela proposes - even after several minutes of analysis and a million nodes - that Black should tennuki at H14. That would snatch defeat from the jaws of certain victory; White would dive into T8 and win the race. I started this thread with the contention that analysis mode can help developers find problems, I hope this example explains why. My theory is that if a program could reliably recognize the outcome of such capturing races five or ten moves sooner, it could crush the likes of me. :D Terry McIntyre terrymcint...@yahoo.com Government is an association of men who do violence to the rest of us. - Leo Tolstoy From: Michael Williams michaelwilliam...@gmail.com To: computer-go computer-go@computer-go.org Sent: Tuesday, April 21, 2009 1:57:54 PM Subject: Re: [computer-go] Reply to Lukasz and Don + Roadmap 2020 Mention the program so that the author can either refute your claim or fix the bug. terry mcintyre wrote: Is it reasonable to expect pro players to use 6-dan programs as a tool for analysis? The pro players are markedly better - at a rough guess, a pro player could give a 6 dan amateur human or program a 3 stone handicap. On the other end of the scale, beginning players and mid kyu players could indeed make good use of an analysis mode by a program which is better than themselves. Lastly, an analysis mode would be helpful to developers, methinks. After winning a game, I like to back up a few moves and find out when the program realized that it was behind. This often happens several moves after the fatal blow has already been struck. I know the feeling too well, when stronger players deftly skewer my group and I only discover the problem five moves later. What do they know that I don't? What do they know that the program doesn't? We have a saying, you learn the most from reviewing games which you have lost. An analysis mode can help developers to discover when their pride and joy first begins to miss the target. Lately, I have been playing quite a bit with a commercially available program. An almost-ladder which has an extra liberty will apparently be evaluated the same as a true ladder, and the program can be tricked into trying to capture my ladder-like position. This sort of predictable flaw might provide a clue to improve the next version. Terry McIntyre terrymcint...@yahoo.com Government is an association of men who do violence to the rest of us. - Leo Tolstoy ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ example.sgf Description: Binary data example2.sgf Description: Binary data ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Reply to Lukasz and Don + Roadmap 2020
Is it reasonable to expect pro players to use 6-dan programs as a tool for analysis? The pro players are markedly better - at a rough guess, a pro player could give a 6 dan amateur human or program a 3 stone handicap. On the other end of the scale, beginning players and mid kyu players could indeed make good use of an analysis mode by a program which is better than themselves. Lastly, an analysis mode would be helpful to developers, methinks. After winning a game, I like to back up a few moves and find out when the program realized that it was behind. This often happens several moves after the fatal blow has already been struck. I know the feeling too well, when stronger players deftly skewer my group and I only discover the problem five moves later. What do they know that I don't? What do they know that the program doesn't? We have a saying, you learn the most from reviewing games which you have lost. An analysis mode can help developers to discover when their pride and joy first begins to miss the target. Lately, I have been playing quite a bit with a commercially available program. An almost-ladder which has an extra liberty will apparently be evaluated the same as a true ladder, and the program can be tricked into trying to capture my ladder-like position. This sort of predictable flaw might provide a clue to improve the next version. Terry McIntyre terrymcint...@yahoo.com Government is an association of men who do violence to the rest of us. - Leo Tolstoy ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Could be that nobody is playing?
From: Jason House jason.james.ho...@gmail.com CGOS requires us to use new names on the server each time we change our bots. It computes the strength using all games (heavilly biased with the results of the first 100 games) Hypothetically speaking, if a bot were to actually learn from experience, how would CGOS deal with that? ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] COGS bug in Ko detection?
Robert, your reference to hane-seki, also called hanezeki, was new to me, so I did a bit of googling. My head is now spinning; I figure that any program which embodies the knowledge in the following paper should be quite interesting: http://www.goban.demon.co.uk/go/seki/hanezeki/hanezeki_abstract.pdf Terry McIntyre terrymcint...@yahoo.com From: Robert Jasiek jas...@snafu.de megasnippage hane-sekis are also pretty ugly. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Fast ways to evaluate program strength.
From: Łukasz Lew lukasz@gmail.com I was wondering what are the good (fast/accurate) ways of evaluating program strength. The most accurate one is to play many games against gnugo or on KGS. But it is quite slow as many games are needed. Another one is to have set of labeled positions (win/loss) and make your program predict the labels. (This is what MoGo guys did) It is much faster. But how well it is correlated with the true strength? If your program were 100% accurate, it would win all winnable games. When any program loses a game, it would be interesting to use deeper search to backtrack, find the blunder which lost the game, and add key positions to the set. Tune your program so that it knows that move A loses, move B wins. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Fast ways to evaluate program strength.
Amen to that. When using positions to judge the strength of a program, one would need to test not just one pro move, but a sequence of plays -- including some which don't appear in pro games. A pro knows how to deal decisively not only with the optimal plays of other pros, but also with suboptimal plays from the rest of us. Programs are often even stranger than human players. If I were designing a test set, I'd ask pros to defeat the program, and would convert the blunders into a test set. To improve, the program would have to generalize the lessons learned from those test cases. Terry McIntyre terrymcint...@yahoo.com -- People never lie so much as after a hunt, during a war or before an election. - Otto von Bismarck From: steve uurtamo uurt...@gmail.com To: computer-go computer-go@computer-go.org Sent: Tuesday, April 7, 2009 5:12:27 PM Subject: Re: [computer-go] Fast ways to evaluate program strength. otherwise pair-go wouldn't be as funny to watch. s. On Tue, Apr 7, 2009 at 8:05 PM, Michael Williams michaelwilliam...@gmail.com wrote: Łukasz Lew wrote: I would like to rephrase my question: Let's measure prediction of pro moves of a whole engine while modifying heavy playouts / MCTS in the engine. How well might it work? Probably not well. Because what matters is not how often you play strong moves, but how often you avoid blunders. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: RE: [computer-go] Pseudo liberties: Detect 2 unique liberties?
From: Heikki Levanto hei...@lsd.dk On Fri, Apr 03, 2009 at 05:07:41PM +0200, Isaac Deutsch wrote: This may seem slow, but it has a couple real advantages. First, it works with the cache to maximize locality. Second it is very simple. This *does* seem slow, even when caching the number of liberties. You mentioned that you did this a couple years ago, do you think it still holds true? Thank you for the information. This is what I do too. I never bothered with bit-arrays but possibly that's simply because I fail to see how you can merge two chains and count liberties in O(1). Merging would be a simple OR operation. Counting can be done, for example, with some kind of binary search. Counting the bits set has been well researched and many different algorithms exist. besides, most often you only need to know if a string has zero, one, two, or many liberties, so the counting can be aborted early. Most cases do test for zero/one/two/many, but if we want smart playouts, it helps to know in advance exactly how many liberties some strings have, compared to others in a capturing race. Any program which assumes that n liberties is enough to live may be tricked by a player who can count to n+1. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] CGT approximating the sum of subgames
From: Jason House jason.james.ho...@gmail.com On Feb 17, 2009, at 4:39 PM, dave.de...@planet.nl wrote: I've been looking into CGT lately and I stumbled on some articles about approximating strategies for determining the sum of subgames (Thermostrat, MixedStrat, HotStrat etc.) Link? http://www.cs.rice.edu/~cra1/Home/Publications_files/icga_vol29_4.pdf looks promising. ( just something I googled up ) ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] static evaluators for tree search
From: dhillism...@netscape.net dhillism...@netscape.net Perhaps the biggest problem came from an unexpected quarter. MC playouts are very fast and neural nets are a bit slow. (I am talking about the forward pass, not the off-line training.) In the short time it took to feed a board position to my net and get the results, I could have run enough MC playouts to obtain a better estimate of the ownership map. :/ Would GPUs be better suited to neural nets than to MC playouts? If so, would this tilt the playing field in favor of neural nets on GPUs,. giving them an advantage over MC on relatively fewer general-purpose CPUs? A GPU with hundreds of shaders is relatively cheap compared to even a handful of x86 processors. The same argument may apply to other forms of classification which map well to GPUs. A Good Credit Score is 700 or Above. See yours in just 2 easy steps! ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Fuego performance
Does Fuego make use of multiple cores? Does it require some switch setting to do so? How do I control the time used by Fuego? ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Poll: how long until computers are as strong as pros?
From: Bob Hearn robert.a.he...@dartmouth.edu How long until a computer beats a pro -- any pro -- in an even game? How long until a computer can routinely beat the best pros? We've recently seen a program with a 7 stone handicap beat a pro, so we're a little bit closer than when you made those computations. I agree with David Fotland, there will be some serious algorithmic improvements; we are hardly scratching the surface at this point. In addition, the computing field in general has been held back for two decades by excessive dependence on the x86 family of architectures; this trend is going to change; performance-per-million-transisters is going to rise sharply in the next decade. Reconfigurable computing has yet to fulfill its aims, but a variety of technologies are likely to come together to make it possible for pro-level computer programs - and a lot of other goodness - within the next 20 years. Something like SGI's Molecule and the Sicortex architectures will make it possible for lots of low-power minimalist computers to be clustered together at comparatively low cost, using less rack space and power. Today's commodity-based clusters waste an amazing amount of hardware. Why should a 4000-node computer have 1000 VGA ports, 1000 disk drives, 1000 disk controllers, 1000 power supplies? We need to create commodity compute modules which are a lot leaner, smaller, cheaper, faster, and more efficient. A compute node should have one or many CPUs, memory controllers, fast inter-node communications, local flash (or a succesor thereof) for boot and other longer-term info, and nothing else - no video, no disk, no independent fans and power supplies, etc. It could fit in a matchbox. A large cluster should fit in a breadbox. Not a very scientific poll, I realize, but I'd like some numbers to use in my AAAS talk on Saturday. FWIW, this is a back-of-the-envelope calculation I did in August, when MoGo beat Myungwan Kim 8p at H9: After the match, one of the MoGo programmers mentioned that doubling the computation led to a 63% win rate against the baseline version, and that so far this scaling seemed to continue as computation power increased. So -- quick back-of-the-envelope calculation, tell me where I am wrong. 63% win rate = about half a stone advantage in go. So we need 4x processing power to increase by a stone. At the current rate of Moore's law, that's about 4 years. Kim estimated that the game with MoGo would be hard at 8 stones. That suggests that in 32 years a supercomputer comparable to the one that played in this match would be as strong as Kim. This calculation is optimistic in assuming that you can meaningfully scale the 63% win rate indefinitely, especially when measuring strength against other opponents, and not a weaker version of itself. It's also pessimistic in assuming there will be no improvement in the Monte Carlo technique. But still, 32 years seems like a surprisingly long time, much longer than the 10 years that seems intuitively reasonable. Naively, it would seem that improvements in the Monte Carlo algorithms could gain some small number of stones in strength for fixed computation, but that would just shrink the 32 years by maybe a decade. Thanks, Bob Hearn - Robert A. Hearn Neukom Institute for Computational Science, Dartmouth College robert.a.he...@dartmouth.edu http://www.dartmouth.edu/~rah/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] GPGPU
- Original Message From: Petr Baudis pa...@ucw.cz There has been some talk about implementing monte-carlo playouts on GPUs in the past, I have heard rumours about Polish bachelor student doing libego - GPGPU conversion as a project, etc. but I know of nothing concrete ever materializing - is anybody aware of anything? We have recently bought very high-end nVidia card at our university department for trying out GPGPU and I'm thinking of a little project for myself, maybe... I'm not much skilled in this kind of programming though, so I'm not quite sure what the best design approach to take would be... my current ideas so far are either (i) Have one game per pipeline, and in each cycle, take a board and transform it by playing a random move (or possibly have an extra cleanup cycles if capturing stones would take too long); you should be able to do some neat pattern matching and so too (ii) Have one intersection per pipeline, in one cycle play a random move, then have board_height cycles for captures and liberty updates to ripple through to all the neighbors. The code would be much more streamlined, but I'm not sure yet if there is a good way to do the rippling - ORing bitmaps? I guess there is a lot of things to try out. There may be ways to implement monte carlo effectively on GPUs - but some other algorithms might make more effective use of the different capabilities of the GPU. For instance, neural networks might map well to a GPU. It might also be possible to collect a lot of useful information about shapes using cellular automata. The GPU might be the main engine, or it might be deployed to collect information about the current board situation ( such as the most interesting plays ) which is then fed to the CPU for creation of a tree structure. Hard to say a priori -- lots of room for experimentation! ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] time measurement
I would not want to discourage remote players - some systems are designed to take advantage of large supercomputers which are not very portable. However, remote players need to accept the trade-off. They get to avoid the trouble of packing up and shipping a trailer full of computer gear to the other side of the world. The downside is that network lag happens. As others have mentioned, client-side timing can be gamed by the simple expedient of pulling the plug to the modem; I can think of a few ways to manipulate iptables which would have similar effects. I hope that tournament organizers do their best to provide a decent connection. Remote participants need to do likewise. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] time measurement
This is the timeseal web site: http://www.unix-ag.uni-kl.de/~chess/soft/timeseal/ Looks like an interesting read. Terry McIntyre terrymcint...@yahoo.com -- Libertarians Do It With Consent! - Original Message From: Jeff Nowakowski j...@dilacero.org To: computer-go computer-go@computer-go.org Sent: Tuesday, February 3, 2009 10:34:32 AM Subject: Re: [computer-go] time measurement On Tue, 2009-02-03 at 10:16 -0800, Ian Osgood wrote: Frankly, I'm baffled that nobody in the online Go world cares about network lag. Timeseal has been a mature technology on the chess servers for over a decade. I logged into FICS today for nostalgia and one of the first thing I see is somebody complaining on channel 53 about somebody lag cheating. It's just a can of worms to require some proprietary binary that people have to use, trust, and believe is unhackable. And remember, pulling your network cable from the wall is an unstoppable hack. -Jeff ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] time measurement
- Original Message From: Gian-Carlo Pascutto g...@sjeng.org Heikki Levanto wrote: No amount on crypto-mumbo-jumbo will solve the problem that the server will have to trust the program, and its author. Signing can provide some little assurance that the program running today is the same as was running yesterday, but that's about all. As long as we can write our own programs, there is no way to stop us from cheating in them, intentionally or by accident. Very true. To the people that point to timeseal on the chess servers: both the binaries and the protocol itself are trivially reverse engineerable. I know of at least 2 people (not counting myself) who have done this. Because the client side is fully under your control, you can cheat all you want with this system. But you can also write a client for a non-supported platform :) The only reason why this doesn't create more problems is that the people who have the ability to do this reverse engineering usually have better things to do with their time than to cheat on chess servers. It's like copy protections: it stops some people, but it sure as hell ain't secure in any meaningful sense. So it's trustworthy enough the people accept it as a palliative for net lag, in an environment where most people can be trusted. From browsing chess-specific web sites, there are customs and procedures for dealing with cheats. In this day and age, unless you're in the boonies, only so much net lag is believable. Preserving one's reputation is a good enough incentive for most people to do the right thing. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] time measurement
Further information, including a helpful diagram: http://www.edcollins.com/chess/lag.htm Terry McIntyre terrymcint...@yahoo.com -- Libertarians Do It With Consent! - Original Message From: terry mcintyre terrymcint...@yahoo.com To: computer-go computer-go@computer-go.org Sent: Tuesday, February 3, 2009 10:59:12 AM Subject: Re: [computer-go] time measurement This is the timeseal web site: http://www.unix-ag.uni-kl.de/~chess/soft/timeseal/ Looks like an interesting read. Terry McIntyre -- Libertarians Do It With Consent! - Original Message From: Jeff Nowakowski To: computer-go Sent: Tuesday, February 3, 2009 10:34:32 AM Subject: Re: [computer-go] time measurement On Tue, 2009-02-03 at 10:16 -0800, Ian Osgood wrote: Frankly, I'm baffled that nobody in the online Go world cares about network lag. Timeseal has been a mature technology on the chess servers for over a decade. I logged into FICS today for nostalgia and one of the first thing I see is somebody complaining on channel 53 about somebody lag cheating. It's just a can of worms to require some proprietary binary that people have to use, trust, and believe is unhackable. And remember, pulling your network cable from the wall is an unstoppable hack. -Jeff ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] RAVE and memory allocation considerations
From: Isaac Deutsch i...@gmx.ch Do you think the spent allocating could be critical? What do you think would be a good way to deal with this? I think to avoid the continuous allocation/deallocation, it's necessary to keep the threads running instead of creating/joining them for each genmove. This would allow them to only have to alloc/dealloc when the board size is changed. If your threads persist from move to move, you will save not only the expense of allocating and deallocating a large memory pool, but also the cost of creating new processes. On the other hand, you will need a quick method of clearing old information from previous nodes. Terry McIntyre terrymcint...@yahoo.com -- Libertarians Do It With Consent! ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: GCP on ICGA Events 2009 in Pamplona
I found a Mind Sports slide presentation which says the following: Go originated in South-East Asia, and the majority of Go players and fans will be found in that area. Private initiative characterises the organisation of Go which explains the strong ties with the media and business. GO is well recognized by Asian people institutions In China, the government strongly supports the organisation and promotion of Go. In Japan Go is recognised as an instrument contributing to key elements of human life, such as young people’s education, leisure activities, mental care for the aged, promotion of culture. In Korea the demand for Go is rising rapidly. A number of Korean youngsters are the top players in the world. They are role models for the Korean youth. In many schools Go is part of the curriculum. Many Go teachers and promoters have travelled around the world and popularised the game of Go. Nowadays, Go is heavily broadcast in Asia: 15 Chinese television networks. Go broke record of TV viewers on CCTV. 3 Korean TV channels are dedicated solely to GO. Japan’s National Station (NHK) organises a tournament running throughout the year which is broadcast for two hours every Sunday, attracting a very large audience. Mind Sports claims there are 60 million Go players and 300 million chess players worldwide. The usgo.org site claims that there are 100 million go players worldwide. I have been told by a Korean professional that the popularity of Baduk in Korea is rising quite rapidly. Terry McIntyre terrymcint...@yahoo.com -- Libertarians Do It With Consent! ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/