Re: [computer-go] U. of Alberta bots vs. the Poker pros
This is a remarkable result. I think poker is more difficult than Go and of course chess. My hypothesis (its just a hypothesis) for the success is. There is someone - Dave Billings - who worked for many years very consequently on the topic. And he is able to motivate a lot of other good people to go along with him. And he gets probably also a lot of support from his boss, J.Schaeffer. And of course, there is some prospect to win fame and money. The conditions for solving a problem are always at least as important than the problem itself. Maybe are the conditions in Poker better than in Go. As said above, I think the problem is in Poker harder. They have of course not solved the whole problem. Heads-Up limit Hold'Em is the - for computers - easiest game. But its nevertheless remarkable that they are on-par with the Poker-GMs. Chrilly - Original Message - From: [EMAIL PROTECTED] To: computer-go@computer-go.org Sent: Thursday, July 26, 2007 6:02 AM Subject: [computer-go] U. of Alberta bots vs. the Poker pros -BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Humans beat poker bot ... barely: http://cosmiclog.msnbc.msn.com/archive/2007/07/25/289607.aspx - -- *** FULL-SPECTRUM DOMINANCE! *** * In advance of the Revolution: * Get facts get organized * * Fight the Man! * thru these sites movements * * Critical endorsement only Most sites need donations * * http://www.buynothingchristmas.org Buy Nothing Christmas * * http://www.aflcio.com/corporateamericaExecutive PayWatch * * [splitURL] /paywatch/ceou/database.cfm Database * * http://www.africaaction.orgAfrica Action * * http://www.msf.org Doctors Without Borders * * http://sweatshopwatch.orgSweatshop Watch * * http://www.maquilasolidarity.org Maquila Solidarity Network * ** Revealed Truth pales in comparison with the method of Science *** GPG fingerprint = 2E7F 2D69 4B0B C8D5 07E3 09C3 5E8D C4B4 461B B771 -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.1 (GNU/Linux) iD8DBQFGqBzQXo3EtEYbt3ERAhQzAJ9GxAD38q8K1pU8Qp7o5Ok6mi3k3wCdHwc4 8w17aqALXM/oib5umPdBDRo= =VmGC -END PGP SIGNATURE- ___ 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] U. of Alberta bots vs. the Poker pros
If one makes e.g. something like Hydra, one has already almost all at hand. There is the work of Ken Thompson, of the Deep Blue team, the work of Frans Morsch, Ed Schroeder... There is an industrial quality infrastructure, databases, interfaces, there are people who have already learned their lesson One is a dwarf standing on the shoulders of giants. The Polaris team had not such an infrastructure, but they build it over many years and with a lot of effort for themself. The effort is comparable to the big chess projects. Not in money terms, but from the man-power investments. In Go their is neither. There is no infrastructure, one is a dwarf standing on the shoulders of dwarfs and their is not such a team like the Polaris one so far. Maybe the INRA group succeeds to make something similar. I have no idea, but I can't see at the moment nobody who works like the Polaris or Deep Blue team. One can discuss, if Go or Poker is harder. Its definetly harder than chess. But I am also convinced, that Go is not that hard, its this poor state of the affairs which makes the problem that hard. Chrilly - Original Message - From: Harri Salakoski [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Thursday, July 26, 2007 11:44 AM Subject: Re: [computer-go] U. of Alberta bots vs. the Poker pros think poker is more difficult than Go and of course chess. I have only studied poker AI basics and coded game rules, learned play slightly winning net poker. But however dare to say my opinion that I totally disagree. Sounds like somekind of poker hype that it is as tough problem than Go game AI 19*19 table. It is offcourse very complex interaction problem but my opinion is that it is still lot of easier problem. It is maybe even possible that it can't be proven and that theory you are right, because poker can be iterated forever and that in theory propably there is _no_ best strategy. I see it very same/similar thing than in super simple iterated prisoners dilemma problem. There just is no best strategy, any strategy has some other dominating strategy, so I have understanded it. But there is very good strategies, every bet when you but your money in table you play even stronger(bluff), play normally or slow play present weaker hand than you actually have. That thing iterated, remembering what opponents have done earlier (like in prisoners dilemma) it is tough problem, but saying it harder than go game is not true at least in practise. In practise I see it so that computers have advantage in poker other things than this complex interaction, where advantage is in humans. As computers can actually calculate odds and propabilities exactly, that advantage is maybe slight, but something which similar don't exist in go-game. But yep just started poker AI in my project http://sourceforge.net/projects/narugo, coded there SimpleActionGenerator, in estimated couple years work it is gonna plays better poker than starter player :| So imho if somebody states that poker is harder AI problem than go-game, it sounds poker hype. t. Harri - Original Message - From: chrilly [EMAIL PROTECTED] To: [EMAIL PROTECTED]; computer-go computer-go@computer-go.org Sent: Thursday, July 26, 2007 10:32 AM Subject: Re: [computer-go] U. of Alberta bots vs. the Poker pros This is a remarkable result. I think poker is more difficult than Go and of course chess. My hypothesis (its just a hypothesis) for the success is. There is someone - Dave Billings - who worked for many years very consequently on the topic. And he is able to motivate a lot of other good people to go along with him. And he gets probably also a lot of support from his boss, J.Schaeffer. And of course, there is some prospect to win fame and money. The conditions for solving a problem are always at least as important than the problem itself. Maybe are the conditions in Poker better than in Go. As said above, I think the problem is in Poker harder. They have of course not solved the whole problem. Heads-Up limit Hold'Em is the - for computers - easiest game. But its nevertheless remarkable that they are on-par with the Poker-GMs. Chrilly - Original Message - From: [EMAIL PROTECTED] To: computer-go@computer-go.org Sent: Thursday, July 26, 2007 6:02 AM Subject: [computer-go] U. of Alberta bots vs. the Poker pros -BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Humans beat poker bot ... barely: http://cosmiclog.msnbc.msn.com/archive/2007/07/25/289607.aspx - -- *** FULL-SPECTRUM DOMINANCE! *** * In advance of the Revolution: * Get facts get organized * * Fight the Man! * thru these sites movements * * Critical endorsement only Most sites need donations * * http://www.buynothingchristmas.org Buy Nothing Christmas * * http://www.aflcio.com/corporateamericaExecutive PayWatch * * [splitURL]
Re: [computer-go] The Problem With Random Playouts
On 7/26/07, Darren Cook [EMAIL PROTECTED] wrote: A couple of months back I wrote an article on why I believe UCT with random playouts (as opposed to heavy playouts) will never give a strong computer go program. I've finally got it finished, edited and published: http://dcook.org/compgo/article_the_problem_with_random_playouts.html I'd be surprised if the UCT experts on this list will find much new there, but I hope some people will find it of value. Thanks to Magnus Persson for reviewing an earlier version. Darren One remark; when you write: What I am calling random playouts for the purposes of this article give all legal moves equal weight and randomly chooses one of them, and this process is used for both players all the way to the end of the game. I get the impression that this also includes filling single point eyes. Is this your intention? Erik ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] The Problem With Random Playouts
What I am calling random playouts for the purposes of this article give all legal moves equal weight and randomly chooses one of them, and this process is used for both players all the way to the end of the game. I get the impression that this also includes filling single point eyes. Is this your intention? No. I was just trying to differentiate from heavier playout schemes that have a random element. I'll change that sentence to be more precise. Thanks for the feedback, Darren ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] The Problem With Random Playouts
On 7/26/07, Darren Cook [EMAIL PROTECTED] wrote: The statement will never give a strong computer go program. is rather devoid of meaning. You either should define strong ... OK, I'll add something. By strong I mean dan level. In that case, the statement seems downright wrong. We know from both theory and Dan's experiments that there is no limit to the strength of UCT with random playouts. Maybe you only meant MC Go without UCT? ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] The Problem With Random Playouts
The statement will never give a strong computer go program. is rather devoid of meaning. You either should define strong ... OK, I'll add something. By strong I mean dan level. I definitely agree that once you've played a few thousand uniformly random games, there is little to be gained by doing a few thousand more. And as an evaluation function this is a relatively weak one - although surprisingly good in some ways it has definite limitations.AnchorMan hits the wall at about 5,000 simulations and it is uniformly random with no other search involved. It would not be much stronger even with infinite number of simulations. 5000 is a fascinating number. You cannot be talking about UCT playouts, as I know you know strength always increases with more playouts. But, if you are talking about playouts as an evaluation function, in my experiments there was practically no gain in accuracy beyond 60 playouts, and even 30 was enough to get a good approximation. I guess our results are so different as I concentrated on the end game? The way to think about a play-out policy is to ask, how good would it be given an infinite number of simulations? The answer for uniform random is, not very. I did not mention it in the article, as it wasn't related to my main point, but when I've been testing playout algorithms I've been measuring the result as 5 sets of 20 playouts, then remembering the worst score of the 5 sets. The difference in accuracy between worst set of 20 and all 100 playouts I've been calling the stability: a small difference is a stable algorithm, and is highly desirable as then I know I can get a reliable estimate with fewer playouts. Darren ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] U. of Alberta bots vs. the Poker pros
On 7/26/07, steve uurtamo [EMAIL PROTECTED] wrote: There is certainly more money to be made in poker than in go. Yes, but its also more difficult. do you mean this in a casual, unsubstantiated way, or in an exact way? My feeling is that there are a lot of people making a lot of money in online poker by having a bot play for them. They don't like to talk about it because they don't want their situation to change. I myself made a go at it. My bot was able to play fully automated 7 card stud on ParadisePoker.com. It had to read the graphical screen to understand what was going on and when it was it's turn, etc. It played decently, but it was too easy for the other players to catch-on to it's strategy. Eventually I lost interest. That was about 4 years ago. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] KGS Tournament Registration
I'd like to register HBotSVN for the open tournament. I forget why we ran HB04 in the last tournament as well, but let me know if that's desired for this tournament. Unfortunately, I don't anticipate significantly enhanced performance for this next tournament. - Name on KGS: HBotSVN - Name of bot: HouseBot 0.6.2 - Authors: The HouseBot development team - Division: Open - My name: Jason House On 7/26/07, Nick Wedd [EMAIL PROTECTED] wrote: The August 2007 KGS computer Go tournament will be on the first Sunday in August, August 5th, in the Asian evening, European morning and American night, starting at 08:00 UTC (GMT) and ending soon after 12:00 UTC (GMT). The Formal division will be a 6-round Swiss with 13x13 boards and 18 minutes each sudden death. The Open division will be an 8-round Swiss with 9x93 boards and 13 minutes each sudden death. Both will use Chinese rules with 7.5 points komi. There are details at http://www.gokgs.com/tournInfo.jsp?id=307 for the Formal division, and at http://www.gokgs.com/tournInfo.jsp?id=308 for the Open. Registration is now open. To enter, please read and follow, as usual, the instructions at http://www.weddslist.com/kgs/how/index.html. The rules are given at http://www.weddslist.com/kgs/rules.html. As for the last two events, please send it (with the words KGS Tournament Registration in the title as usual) to me at maproom at gmail dot com (converted to a valid address in the obvious way). I will be away from home next Monday, Tuesday, and maybe Wednesday. If I do not receive your registration by the evening of Sunday 29th, I may not act on it until Thursday 2nd. Nick -- Nick Wedd[EMAIL PROTECTED] ___ 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] U. of Alberta bots vs. the Poker pros
- Original Message - From: steve uurtamo [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Thursday, July 26, 2007 7:29 PM Subject: Re: [computer-go] U. of Alberta bots vs. the Poker pros i think that you might be confusing two important things: i) the difficulty of a problem. ii) the amount and kind of effort that has gone toward solving a problem. No, not at all. But my point is: For progress in any field the difficulty of a problem is less important than the urgency/interest of society to solve it. Science and technology is not driven by the internal logic of the science, but by the interest of the society. Once there is a very high social demand, there is big progress in a field. There is the proverb war is the mother of all things. A lot of innovations are made related to war. In times of war the social urgency is highest and costs do not matter. E.g. the atomic bomb was build within a short time, jet-propulsion, computers were developed .. In medicine progress is made, if it is a rich-mans sickness, and almost no progress is made if its a poor-mans fate. E.g. There is considerable advancement in AIDS-medicine, because it was at least initially a rich-mans sickness, there is almost no progress in Lepra. This can not be explained by the intrinsic difficulties of the deseases. It is also quite a hard problem to generate realistic 3D effects in real-time. There is high social interest (the kids have enough money), so one develops special purpose massive parallel hardware like the latest graphics cards or the Cell processor. The action players and not anymore the D.O.D. are nowadays the driving force behind hardware-development. If there would be the same interest for Go, one could develop special purpose Go-Hardware with an impressive speedup. But Go is like Lepra. Chrilly ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] U. of Alberta bots vs. the Poker pros
I don't understand this. For a given hand the odds of winning can be easily calculated for poker and the best play can be formulated accordingly. It's like to program a com[uter to win a coin toss. I would be surprised if any side win big. The only thing a computer can to is to model opponent's behavior, which may deviate from the best play. What did I miss? DL AOL now offers free email to everyone. Find out more about what's free from AOL at AOL.com. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] U. of Alberta bots vs. the Poker pros
Every hand has theoretical winning propability but if you bet exactly according winning odds you tell too much about your hand, other players fold and call and raise according your bets, only when they think they have better cards, that is bad, obivious book play works only starter levels. In poker you example should not raise too much, very often opponent has for example nuts, such cards that they can't lose, so it is stupid to but all your money in if there is very little money in bot. If you raise too little that is bad either as you not get full value of your good cards and turn or river can give better cards for opponents. I don't think have you mist anything, but _modeling opponents behaviour_, that is quite much ask from bot. So what is best play, it depends also how you play, but how bot plays, humans are good for observer simplified behaviour and find weak points from bot. Other hand I think that it should be possible easily measure bots quality, even lot faster and easier than in go game as one hand typically can be played very fast. You could play in one 300 turn go-game 300 poker rounds, so quality of poker bots should be easily evaluated, in 1 rounds small differences start to show up, but that is maybe out of topic. So following things should fafor bot in poker: Exact mathematic. Exact memory is possible. In Prisoners dilemma, atleas if you remember longer opponent moves than your opponent remembers your moves, it does not quarantee your win but it makes it easier if you can use your data right. Bot don't lose temper, and don't care if it is losing or not, attleast starter levels thats not case in humans. Also like money poker is quite much waiting for opportunity and bot should have time to wait. Practical issues are imho much more demanding in go-game AI than in poker AI. For example generating random table in go-game and poker was nice to notice how easy it is generate random flop in poker... t. Harri - Original Message - From: [EMAIL PROTECTED] To: computer-go@computer-go.org Sent: Friday, July 27, 2007 4:26 AM Subject: Re: [computer-go] U. of Alberta bots vs. the Poker pros I don't understand this. For a given hand the odds of winning can be easily calculated for poker and the best play can be formulated accordingly. It's like to program a com[uter to win a coin toss. I would be surprised if any side win big. The only thing a computer can to is to model opponent's behavior, which may deviate from the best play. What did I miss? DL -- AOL now offers free email to everyone. Find out more about what's free from AOL at AOL.com. -- ___ 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] U. of Alberta bots vs. the Poker pros
As I understand it, bots can try to estimate and play at the Nash equilibrium. In some sense, that is optimal. Alternatively/additionally the bot can deviate from equilibrium play based on opponent modelling. Finding the NE is hard. I think that is why the rules are restricted, to make it easier to find the NE. - George On 7/26/07, Dave Dyer [EMAIL PROTECTED] wrote: The only thing a computer can to is to model opponent's behavior, which may deviate from the best play. What did I miss? No, you didn't miss a thing. I look forward to meeting you at a poker table, preferably with high stakes. ___ 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] U. of Alberta bots vs. the Poker pros
In message [EMAIL PROTECTED], Chris Fant [EMAIL PROTECTED] writes On 7/26/07, steve uurtamo [EMAIL PROTECTED] wrote: There is certainly more money to be made in poker than in go. Yes, but its also more difficult. do you mean this in a casual, unsubstantiated way, or in an exact way? My feeling is that there are a lot of people making a lot of money in online poker by having a bot play for them. They don't like to talk about it because they don't want their situation to change. I myself made a go at it. My bot was able to play fully automated 7 card stud on ParadisePoker.com. It had to read the graphical screen to understand what was going on and when it was it's turn, etc. It played decently, but it was too easy for the other players to catch-on to it's strategy. Eventually I lost interest. That was about 4 years ago. Commercial poker servers forbid the use of bots, and invest some effort in detecting and punishing them (by confiscating their funds). To encourage human customers, they boast of how effective they are at this. People who use poker bots generally keep quiet about it. So when poker bots are discussed, both sides have an interest in downplaying their prevalence. This results in a consensus which IMHO is likely to be some way wide of the truth. Nick -- Nick Wedd[EMAIL PROTECTED] ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] U. of Alberta bots vs. the Poker pros
Both. Its probably not so difficult to make a simple bot. But it is also not difficult to make a simple UCT player. But I am sure, that reaching the level of Polaris is more difficult than writing the best Go-programm. I have the feeling, that Polaris is a very serious project. Its certainly not possible to beat it out from nothing like Crazy Stone and MoGo have beaten the Go programms. There is also a lot of work in these 2 programms too and it is not really out of nothing. But its nevertheless not comparable to the work the Billings-group has done. There is also a very large gap between Polaris and the rest. Without Polaris, everybody would say: Oh, its as difficult as Go, the programms are in relation to humans at about the same level. And now Polaris is strong and the argument is: This is because Poker is much easier. No, they have done a better job. i think that you might be confusing two important things: i) the difficulty of a problem. ii) the amount and kind of effort that has gone toward solving a problem. people have been playing go for (depending upon how you judge the gaps) a few thousand years, and yet some of the biggest advances in opening theory have happened in the last fifty years. probably there are many more significant advances that can be made in the opening and the middle game. can the same be said for poker? aside from the (arguably interesting, but perhaps not complicated) fact that your opponent is allowed to misrepresent his situation, a computer program really just has a few simple inputs to deal with -- those cards that it can see, and those bets/folds that people have made. the total number of complete games that a poker program might be expected to play is based upon the number of different cards that it can be expected to see, the maximum number of choices that it may have to make, the number of different bets (or categories of differently-sized bets) that its opponents can make, and perhaps the total number of different opponents that it might be expected to play and where each of those players are seated at the table. i think that it's clear that the size of the problem is smaller (and that our ability to measure being good at the game is less clearly defined) than go. imperfect information does not necessarily mean that a problem is harder. (just as perfect information does not necessarily make a problem hard). if you (say) flip a coin ten thousand times and keep track of the number of heads and tails that you get, i can guess that number to reasonable accuracy even though i have absolutely no information about the actual value other than the process that you used to generate it. if i were to place bets after each and every flip, i could lose all kinds of money playing this game, but that wouldn't mean that i didn't have a perfect strategy. one confusing thing about measuring the ability of a computer poker player play is that even if it loses ten times in a row, it might be the best player at the table. the very best poker players in the world do not consistently win championships, because (as i believe someone else (jacques?) said) the variance is so large. imagine trying to set up ELO rankings for poker players and what would happen to everyone's ranking after each tournament. you could probably establish some broad categories (poor, good, better, best), but it would be difficult to establish exact rankings inside these categories. this doesn't mean that the game is harder, it means that our ability to determine skill is very impaired. go, on the other hand, has, arguably, over 35 independent skill levels, and determining which of these your program is at is a quite simple task. so it's quite easy to measure how successful modern computer go players are. how would we do the same for computer poker players? what's a good measure? what would perfect play look like, and what would the variance in win/loss rate look like against human players? for that matter, what would the variance be among a table composed entirely of perfect computer players? s. Shape Yahoo! in your own image. Join our Network Research Panel today! http://surveylink.yahoo.com/gmrs/yahoo_panel_invite.asp?a=7 ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] U. of Alberta bots vs. the Poker pros
On Thu, 2007-07-26 at 18:14 +0200, chrilly wrote: Chess/Go... can be played in an autistic way. There is no need for an opponent model. Ah, an opponent model. Where's the poision? http://www.imdb.com/title/tt0093779/quotes#qt0250635 Too much rock, paper, scissors in poker for my tastes. Can there ever be a best player? At least in Go the differences in strength are very clear, and some guy off the street who learned the game a year ago is not going to win a tournament. -Jeff ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] U. of Alberta bots vs. the Poker pros
- Original Message - From: steve uurtamo [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Thursday, July 26, 2007 5:17 PM Subject: Re: [computer-go] U. of Alberta bots vs. the Poker pros There is certainly more money to be made in poker than in go. Yes, but its also more difficult. do you mean this in a casual, unsubstantiated way, or in an exact way? Both. Its probably not so difficult to make a simple bot. But it is also not difficult to make a simple UCT player. But I am sure, that reaching the level of Polaris is more difficult than writing the best Go-programm. I have the feeling, that Polaris is a very serious project. Its certainly not possible to beat it out from nothing like Crazy Stone and MoGo have beaten the Go programms. There is also a lot of work in these 2 programms too and it is not really out of nothing. But its nevertheless not comparable to the work the Billings-group has done. There is also a very large gap between Polaris and the rest. Without Polaris, everybody would say: Oh, its as difficult as Go, the programms are in relation to humans at about the same level. And now Polaris is strong and the argument is: This is because Poker is much easier. No, they have done a better job. In the exact way its comparing different things. The state space is in Go larger, but Go is from the mathematical point of view in the trivial class: Finite, Full-Information, 2 Players, Deterministic, Zero-Sum. Poker has a random-player and hidden information. In the general case its an N-player. Chess/Go... can be played in an autistic way. There is no need for an opponent model. Just play the best moves. In poker one needs an opponent model. The game-theoretic optimal strategy is only in special cases sufficient. The Polaris-Human match played also the most simple version. Heads-Up Limited. Non-Limited is already much more complicated, because the implied odds have a much greater variance. Or in other words: The opponent-model is much more important in non-limited. In the N-persons version, the state-space explodes too and in this case its not even clear, what a perfect strategy is. I assume Polaris would not be able to be top ranked in the Poker world-series. It would never come in the final round to play Heads-up. The humans would also form a coalition to kick it out at the beginning and real competition would start only afterwards. Chrilly ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] U. of Alberta bots vs. the Poker pros
There is certainly more money to be made in poker than in go. Yes, but its also more difficult. do you mean this in a casual, unsubstantiated way, or in an exact way? s. Moody friends. Drama queens. Your life? Nope! - their life, your story. Play Sims Stories at Yahoo! Games. http://sims.yahoo.com/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] The Problem With Random Playouts
On Thu, 2007-07-26 at 05:21 -0700, steve uurtamo wrote: The way to think about a play-out policy is to ask, how good would it be given an infinite number of simulations? The answer for uniform random is, not very. really? Again it depends on your definition of good. My main point is that after a few thousand simulations it doesn't improve very much and it never gets remotely close to perfect. However, that doesn't mean it's not good, that depends on what your standard of reference is.I suspect an infinite number of simulations as an evaluation function is a pretty reasonable evaluation function. Not close to perfect by any means but certainly but what evaluation function is? If you could actually compute this quickly, it might be a very good practical evaluation function for a highly selective alpha beta searcher. Please note that you do not have to play an infinite number of play-outs to compute what the expected score of such an evaluation function should be. There is probably no fast way to compute it, but it could be calculated recursively by counting the number of legal moves at each level down to the end of the game and doing some simple math. Of course this is a hypothetical calculation since this would require more computing power than we can muster. - Don s. Park yourself in front of a world of choices in alternative vehicles. Visit the Yahoo! Auto Green Center. http://autos.yahoo.com/green_center/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] Why Poker-GMs don't win at poker.
Chrilly Donninger wrote: I think poker is more difficult than Go and of course chess. Poker can be analyzed well by (even naif) Monte Carlo methods. Of course, the fact that you get a better estimate than any human could dream of, won't necessarily make you win. This common misconception can be found in many computer go papers. People who train patterns to predict moves tend to think the more they predict the better. Some even claim 60% prediction rates and higher. Of course, we all predict moves as a play when we watch pro games and feel good when our guess is right. Two reasons make it easy to have high prediction rate: a. forced moves b. local play is easier to analyze than the value of all possible tenukis. Usually, you don't do very wrong answering local and postponing other fights. My case: I have to give Bradley Terry scores to 1/3 M patterns: LoadJeitoLibRW_ByName() Importance of database loaded # of imp = 32 91986 (91986) # of imp = 31 25466 (117452) # of imp = 30 20263 (137715) # of imp = 29 18556 (156271) # of imp = 28 17592 (173863) # of imp = 27 17646 (191509) # of imp = 26 17722 (209231) # of imp = 25 18575 (227806) # of imp = 24 19283 (247089) # of imp = 23 20525 (267614) # of imp = 22 21695 (289309) # of imp = 21 23712 (313021) # of imp = 20 25434 (338455) Note: The importance of a pattern is the number of disjoint sets of games where the pattern is found if you divide the whole database in 32 disjoint sets. E.g. A pattern of importance 28 is a pattern found in 28 sets of about 1500 games but not found in 4 sets of the same size. I don't collect data on the number of games in which each pattern is found. Note: These are the real untricked patterns. Then, I generate a crunched version that behaves mostly like the big one. So I have 338455 patterns of importance 32 to 20 I could try to maximize the probability of a guess, but I don't! What I really am interested in is _a probability distribution over the legal moves_. I ask my HSB board to give me the _minimum number of moves_ that cover a 30%, 50%, 99% probability. (Note: This number is not an integer. Eg. If it is 3.17 - If the winning move is in the 3 first, you add 1, if it is the fourth move you add 0.17 and else you add 0.) The legal moves are sorted in descending score. For adjusting my Bradley Terry models I have a loss function and a very naif method that corrects in small steps. (The good thing of off-line learning is that you can implement junk because that does not go into the program. ;-) The program updates a pattern and finds its score in two digit nanosecond times ( 400 clock cycles) if it may have changed, and 0 if it may not.) My loss function evaluates (using a random sample from an independent test set) if: When I want 50% I really get 50% (and the same for other values, of course.) If I want 50%, getting 60% is as bad as getting 40%!! What I need is a reliable distribution not a thing that guesses many times. And also, that this distribution contains the maximum information (but that is another story). This explains why when you watch the European Poker Tour on TV and the journalist identifies half a dozen legends including previous year's world champ, US guest don't-know-what-champion Las Vegas, and all other celebrities, none of the legends wins except by a fluke just like anyone else. Statistics is not about winning the lottery, its about getting good estimators. And computer poker programs do better than humans but that does not make them win. Jacques. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] Differences..
What is the difference in Go and Mathematical Go? http://brooklyngoclub.org/jc/rulesgo.html Is Mathamatical Go a subset of Go as the rules look the same to me as regular go. -Josh ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] U. of Alberta bots vs. the Poker pros
The only thing a computer can to is to model opponent's behavior, which may deviate from the best play. What did I miss? No, you didn't miss a thing. I look forward to meeting you at a poker table, preferably with high stakes. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Differences..
Willing to accept the intuitive proof for the moment, what I see is that the key differences are that 1) there is no komi (black giving points to white for playing first) 2) there is a 2 point penalty for each living group. Otherwise it does look like this is similar to any other Go rules that include positional super-ko. My favorite line: this is a great book if you're a serious mathematician, and a completely baffling one otherwise. Cheers, David On 26, Jul 2007, at 7:05 PM, Joshua Shriver wrote: What is the difference in Go and Mathematical Go? http://brooklyngoclub.org/jc/rulesgo.html Is Mathamatical Go a subset of Go as the rules look the same to me as regular go. -Josh ___ 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] U. of Alberta bots vs. the Poker pros
Already invented. There is the Alberta Poker-Server. Chrilly - Original Message - From: Chris Fant [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Thursday, July 26, 2007 6:16 PM Subject: Re: [computer-go] U. of Alberta bots vs. the Poker pros Someone start a CGOS-like poker server for bots. ~10 person tables, No Limit Texas Hold-em. ___ 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] U. of Alberta bots vs. the Poker pros
Someone start a CGOS-like poker server for bots. ~10 person tables, No Limit Texas Hold-em. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] U. of Alberta bots vs. the Poker pros
I think you mean Darse Billings. Yes, sorry, I can not remember names. There is certainly more money to be made in poker than in go. Yes, but its also more difficult. Chrilly ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] U. of Alberta bots vs. the Poker pros
On 7/26/07, chrilly [EMAIL PROTECTED] wrote: This is a remarkable result. I think poker is more difficult than Go and of course chess. My hypothesis (its just a hypothesis) for the success is. There is someone - Dave Billings - who worked for many years very consequently on the topic. And he is able to motivate a lot of other good people to go along with him. And he gets probably also a lot of support from his boss, J.Schaeffer. And of course, there is some prospect to win fame and money. I think you mean Darse Billings. Playing internet poker used to be accomplished only by using shudder IRC /shudder, and Darse was one of the first to automate IRC poker, at first with aliases that folks just shared with each other, informally, then later with gui front-ends, but the back-end was still IRC. I had the privilege of being on the IRC poker server when Poki made its first appearance. Poki was the first incarnation of Darse's poker bot, and it not only played a respectable game of Texas Hold 'Em, it would also respond to chat requests such as Poki, quote Steve, wherupon it would reproduce a joke by comedian Stephen Wright. Darse was not only smart, he was very friendly and helpful to folks, even those who, although they lacked computer knowledge, wanted to play online poker. Such was the infancy of internet poker. Then along came the world-wide web, and now there are dozens, if not hundreds, of poker servers and their associated clients; it has become a multimillion-dollar industry. The conditions for solving a problem are always at least as important than the problem itself. Maybe are the conditions in Poker better than in Go. There is certainly more money to be made in poker than in go. -- Rich ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Differences..
Where does the two-point penalty come from? It's not directly stated in the rules, so presumably it emerges from the four simple rules. Actually, neither the two-point penalty nor Komi are meaningful - there is no count to which any penalties could be added or subtracted. Passing, suicide, and superko are prohibited. Available moves eventually diminish to zero. The person with the smallest territory loses, unable to make a legal move. Terry McIntyre [EMAIL PROTECTED] They mean to govern well; but they mean to govern. They promise to be kind masters; but they mean to be masters. -- Daniel Webster - Original Message From: David Doshay [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Thursday, July 26, 2007 8:02:17 PM Subject: Re: [computer-go] Differences.. Willing to accept the intuitive proof for the moment, what I see is that the key differences are that 1) there is no komi (black giving points to white for playing first) 2) there is a 2 point penalty for each living group. Otherwise it does look like this is similar to any other Go rules that include positional super-ko. My favorite line: this is a great book if you're a serious mathematician, and a completely baffling one otherwise. Cheers, David On 26, Jul 2007, at 7:05 PM, Joshua Shriver wrote: What is the difference in Go and Mathematical Go? http://brooklyngoclub.org/jc/rulesgo.html Is Mathamatical Go a subset of Go as the rules look the same to me as regular go. -Josh ___ 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/ Park yourself in front of a world of choices in alternative vehicles. Visit the Yahoo! Auto Green Center. http://autos.yahoo.com/green_center/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] U. of Alberta bots vs. the Poker pros
This is a remarkable result. I think poker is more difficult than Go and of course chess. for people, or computers? poker is a much smaller game than go. s. Fussy? Opinionated? Impossible to please? Perfect. Join Yahoo!'s user panel and lay it on us. http://surveylink.yahoo.com/gmrs/yahoo_panel_invite.asp?a=7 ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] The Problem With Random Playouts
On Thu, 2007-07-26 at 21:43 +0900, Darren Cook wrote: The statement will never give a strong computer go program. is rather devoid of meaning. You either should define strong ... OK, I'll add something. By strong I mean dan level. I definitely agree that once you've played a few thousand uniformly random games, there is little to be gained by doing a few thousand more. And as an evaluation function this is a relatively weak one - although surprisingly good in some ways it has definite limitations.AnchorMan hits the wall at about 5,000 simulations and it is uniformly random with no other search involved. It would not be much stronger even with infinite number of simulations. 5000 is a fascinating number. You cannot be talking about UCT playouts, as I know you know strength always increases with more playouts. But, if you are talking about playouts as an evaluation function, in my experiments there was practically no gain in accuracy beyond 60 playouts, and even 30 was enough to get a good approximation. Actually, I'm not being accurate here. 5000 play-outs using a modification of all-as-first is about as good as it gets for AnchorMan. But it's measurably better than 2500 play-outs for instance. There is no tree search using this method. I just play these 5000 games randomly and look to see which moves were included the most for the winning side. 60 is preposterous. You are clearly doing something differently, or have a broken algorithm or a really good algorithm. I also found that if you just treat MC play-outs as an evaluation function on top of a tree search, more simulation is better. I guess our results are so different as I concentrated on the end game? In the endgame, less simulations probably give the right answer more often. The way to think about a play-out policy is to ask, how good would it be given an infinite number of simulations? The answer for uniform random is, not very. I did not mention it in the article, as it wasn't related to my main point, but when I've been testing playout algorithms I've been measuring the result as 5 sets of 20 playouts, then remembering the worst score of the 5 sets. The difference in accuracy between worst set of 20 and all 100 playouts I've been calling the stability: a small difference is a stable algorithm, and is highly desirable as then I know I can get a reliable estimate with fewer playouts. But I'm measuring based on actual game playing performance. Darren ___ 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] Differences..
The 2 points per living group comes from the fact that in order to avoid loosing, one plays into one's own territory until down to 2 eyes. While legal to fill one, that leads to capture, so it won't be done. As you say, there is no other counting needed because the smaller territory fills first. Cheers, David On 26, Jul 2007, at 8:25 PM, terry mcintyre wrote: Where does the two-point penalty come from? It's not directly stated in the rules, so presumably it emerges from the four simple rules. Actually, neither the two-point penalty nor Komi are meaningful - there is no count to which any penalties could be added or subtracted. Passing, suicide, and superko are prohibited. Available moves eventually diminish to zero. The person with the smallest territory loses, unable to make a legal move. Terry McIntyre [EMAIL PROTECTED] They mean to govern well; but they mean to govern. They promise to be kind masters; but they mean to be masters. -- Daniel Webster - Original Message From: David Doshay [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Thursday, July 26, 2007 8:02:17 PM Subject: Re: [computer-go] Differences.. Willing to accept the intuitive proof for the moment, what I see is that the key differences are that 1) there is no komi (black giving points to white for playing first) 2) there is a 2 point penalty for each living group. Otherwise it does look like this is similar to any other Go rules that include positional super-ko. My favorite line: this is a great book if you're a serious mathematician, and a completely baffling one otherwise. Cheers, David On 26, Jul 2007, at 7:05 PM, Joshua Shriver wrote: What is the difference in Go and Mathematical Go? http://brooklyngoclub.org/jc/rulesgo.html Is Mathamatical Go a subset of Go as the rules look the same to me as regular go. -Josh ___ 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/ Take the Internet to Go: Yahoo!Go puts the Internet in your pocket: mail, news, photos more. ___ 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] Differences..
So, with these exchanges and just a little more thought, the part of The Alternating Rule that is in red: The first player who cannot put down a stone without breaking a rule loses the game is not the way the game would actually be played. It would be more accurate to add something about choosing not to add another stone, which would cover the decision not to fill one of your own last eyes. Cheers, David On 26, Jul 2007, at 9:12 PM, David Doshay wrote: The 2 points per living group comes from the fact that in order to avoid loosing, one plays into one's own territory until down to 2 eyes. While legal to fill one, that leads to capture, so it won't be done. As you say, there is no other counting needed because the smaller territory fills first. Cheers, David On 26, Jul 2007, at 8:25 PM, terry mcintyre wrote: Where does the two-point penalty come from? It's not directly stated in the rules, so presumably it emerges from the four simple rules. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
