Re: [computer-go] Re: Explanation to MoGo paper wanted.
>In Go things are insofar worse as there is only one standard sparring >partner, Gnu-Go. This creates severe inbreeding effects. In chess there was >a similar problem. There were more strong opponents around, but over the >years they become very similar. Suddenly there was a new programm, Rybka, >which plays different and all the inbreedings have a lot of difficulties. > >I think there is no better way. One can do some pre-filtering with test >positions. If a version is especially bad in these tests, one can ignore it. >But being good in test positions and in games are different things. When MonteGNU is published, it will be an alternative of GNU Go. Of course MC vs MC may have some problems, but at least it is stronger than GNU Go on 9x9. And, if the way to combine UCT and the local tactical search is discovered, the regression test like GNU Go will be also useful. -- Yamato ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Explanation to MoGo paper wanted.
Peter Drake said: > I think Steve meant that the move /should have been used as/ a ko The burning of ko threats is just a narrow example of what I was talking about: what's called "aji keshi." That is, the exchange of a threat for a forced response, prematurely eliminating the potential for more effective attacks later. Part of why I doubt you'll get anywhere with monte carlo on a 19X19 board without some drastic (and highly sophisticated!) pruning of the tree to be explored. Forrest Curo - This email was sent using AIS WebMail. http://www.americanis.net/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Explanation to MoGo paper wanted.
I think Steve meant that the move /should have been used as/ a ko threat. Peter Drake http://www.lclark.edu/~drake/ On Jul 6, 2007, at 5:12 PM, Don Dailey wrote: On Fri, 2007-07-06 at 16:52 -0700, steve uurtamo wrote: The attack is easily refuted with a capture, and when that happens no time was lost. But the opponent must capture immediately or the threat Lazarus made actually works. this, in fact, is a ko threat. if you play it *outside* of a ko, then it's a wasted ko threat. no big loss if there are no kos expected and no lost kos have happened. otherwise it's more tricky. How is this a ko threat? Lazarus threatens a chain of 4 or 5 stones with a self-atari move. If the opponent captures, where is the ko? If the opponent doesn't capture, where is the ko? - Don _ ___ Be a better Heartthrob. Get better relationship answers from someone who knows. Yahoo! Answers - Check it out. http://answers.yahoo.com/dir/?link=list&sid=396545433 ___ 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: Explanation to MoGo paper wanted.
On Fri, 2007-07-06 at 16:52 -0700, steve uurtamo wrote: > > The attack is easily > > refuted with a capture, and when that happens no time was lost. But > > the opponent must capture immediately or the threat Lazarus made > > actually works. > > this, in fact, is a ko threat. if you play it *outside* of a ko, then it's a > wasted ko threat. no big loss if there are no kos expected and no > lost kos have happened. otherwise it's more tricky. How is this a ko threat? Lazarus threatens a chain of 4 or 5 stones with a self-atari move. If the opponent captures, where is the ko? If the opponent doesn't capture, where is the ko? - Don > > > > > > > > Be a better Heartthrob. Get better relationship answers from someone who > knows. Yahoo! Answers - Check it out. > http://answers.yahoo.com/dir/?link=list&sid=396545433 ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Explanation to MoGo paper wanted.
steve uurtamo said: >>There is one other issue I have seen that is similar. Sometimes >> Lazarus will play a move that doesn't hurt nor help it's position. It's >> not a wasted move because the opponent must respond or else lose. > > this sounds a good bit like a ko threat, which is tricky to distinguish > from a good play.nfo/computer-go/ To play a ko threat in a ko fight is usually good play. To play such moves anytime else is a really insidious bad habit, one difficult to extinguish for anyone who assumes "forced moves" are necessarily a good thing. One can burn a lot of opportunities this way without even knowing they were ever there. Forrest Curo - This email was sent using AIS WebMail. http://www.americanis.net/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Explanation to MoGo paper wanted.
> The attack is easily > refuted with a capture, and when that happens no time was lost. But > the opponent must capture immediately or the threat Lazarus made > actually works. this, in fact, is a ko threat. if you play it *outside* of a ko, then it's a wasted ko threat. no big loss if there are no kos expected and no lost kos have happened. otherwise it's more tricky. s. Be a better Heartthrob. Get better relationship answers from someone who knows. Yahoo! Answers - Check it out. http://answers.yahoo.com/dir/?link=list&sid=396545433 ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Explanation to MoGo paper wanted.
On Fri, 2007-07-06 at 15:49 -0700, steve uurtamo wrote: > >There is one other issue I have seen that is similar. Sometimes > >Lazarus will play a move that doesn't hurt nor help it's position. > >It's not a wasted move because the opponent must respond or else lose. > > this sounds a good bit like a ko threat, which is tricky to distinguish > from a good play. It's not a ko threat. Lazarus will attack a fairly small group inside of territory that is controlled by the opponent. The attack is easily refuted with a capture, and when that happens no time was lost. But the opponent must capture immediately or the threat Lazarus made actually works.It's as if Lazarus just wants to see if a quick cheap shot will work. Of course having it do this inside the tree, is a distraction. It's like a horizon effect in chess, a pointless check to kill 2 ply. - Don > s. > > > > > > > > Sick sense of humor? Visit Yahoo! TV's > Comedy with an Edge to see what's on, when. > http://tv.yahoo.com/collections/222 > ___ > 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: computer-go Digest, Vol 36, Issue 6
Yes, it can be done quite quickly in certain circumstances: http://www.lclark.edu/~drake/go/icai2006-final-drake.pdf The problem, of course, is that by the time it's down to this, it's often too late. Peter Drake http://www.lclark.edu/~drake/ On Jul 6, 2007, at 3:55 PM, steve uurtamo wrote: as far as killing moves are concerned, there's a fairly well- understood set of circumstances for groups with a large "blob" eyespace under which death is guaranteed, life is guaranteed if a ko is won, or death is guaranteed if a ko is lost. i have no idea how to weight the last two, but given that you can determine contiguous eyespace, this might be a cheap thing to code in. 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/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: computer-go Digest, Vol 36, Issue 6
as far as killing moves are concerned, there's a fairly well-understood set of circumstances for groups with a large "blob" eyespace under which death is guaranteed, life is guaranteed if a ko is won, or death is guaranteed if a ko is lost. i have no idea how to weight the last two, but given that you can determine contiguous eyespace, this might be a cheap thing to code in. 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] Re: Explanation to MoGo paper wanted.
> If an improvement is worth 100 Elo, there is no need for extensive testing. > One sees this immediatly. In fact also smaller improvements are in the end > chosen by intuition/feeling. if the win rate is close to 50% (and you can tweak things so that this is the case), you can get away with a smaller number of experiments, using a good significance test to make sure that it's actually an improvement. it only gets really ugly if you are either close to 0% win rate, or close to 100% win rate, in which case it's nearly impossible to measure progress. s. Pinpoint customers who are looking for what you sell. http://searchmarketing.yahoo.com/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: Explanation to MoGo paper wanted.
>There is one other issue I have seen that is similar. Sometimes >Lazarus will play a move that doesn't hurt nor help it's position. >It's not a wasted move because the opponent must respond or else lose. this sounds a good bit like a ko threat, which is tricky to distinguish from a good play. s. Sick sense of humor? Visit Yahoo! TV's Comedy with an Edge to see what's on, when. http://tv.yahoo.com/collections/222 ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Genetic playout algorithms
Darren Cook wrote:? > I've been toying with the idea of having a set of playout algorithms and? > allowing black and white to choose different algorithms in that playout.? > (The idea came from trying to think how I could apply genetic? > algorithms to UCT playouts.)? >? > Here's how it would work. Assume you have 4 algorithms, A/B/C/D, some? > aggressive, some defensive, etc. All with a random element. For the? > first 16 playouts you try all combinations:? > Black uses A, White uses A;? > Black uses A, White uses B;? > ...? > Black uses D, White uses D;? > I've experimented?along these lines a fair amount. It's a fun co-evolution problem. Intransitivity plays a critical role. To picture it, assume you start from an arbitrary board position and start by evolving against a pure random playout strategy. Hopefully, the GA will quickly learn a playout strategy that plays good moves more frequently. Now the GA begins to evolve against the new strategy. The new strategy is stronger, in a sense, but it's also more predictable, so the GA will find a counter that exploits its weakness. It might learn a good general rule (in the context of the particular board state), but it's usually easier to find a stupid gimmick. This counter strategy will tend to be more predictable still. So the natural trajectory leads to more predictable, more brittle solutions until it resembles a game of scissors, paper, stone. You can try to control the level of determinism in the playouts externally. But beware: co-evolution is uncannily good at finding tricky ways to sidestep constraints. When one stops the GA, none of the playout strategies, in the final population, are likely to be suitable for use in UCT. But some properties from the playouts, averaged over time, can hold good information. Or not: there are a lot of ways for the GA to get stuck and forget how to counter a stupid gambit. (A hall of champions helps.) There has been some recent discussion on the list of "stronger" playout strategies that perform worse in the context of UCT. I think that sounds natural when you look at the problem from this perspective. Another aspect of this approach (and I'm certain others have thought of it as well) is to use a GA to produce the same weights that all-as-first does. I did these experiments before CrazyStone or Mogo hit the scene. I had a tree search-Monte Carlo hybrid program, but it was bad by any standards. Now that I've learned more, I may try the GA again some day. - Dave Hillis Check Out the new free AIM(R) Mail -- Unlimited storage and industry-leading spam and email virus protection. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: 9x9 games wanted
I believe the cgos server keeps all of it's games. Though those are all computer games. Might help -Josh On 7/6/07, Tom Cooper <[EMAIL PROTECTED]> wrote: It might be worth asking the administrators of some go servers if they would be prepared to give you copies of some games. At 17:09 06/07/2007, you wrote: >I will play with Suzie at the forthcoming European Go championship >in Villach/Austria some 9x9 demonstration matches against everybody >who wants to play. >I want to prepare an opening book and I am looking for a 9x9 games >collection. So far I have only found in total 244 games, which is >for a book much too less (I am used to have the CB-Megabase). >Is there a larger collection with at least >= 5 Amateur Dan Level available? >If the price is reasonable, I am willing to pay for a professionally >made collection. > >Chrilly >___ >computer-go mailing list >computer-go@computer-go.org >http://www.computer-go.org/mailman/listinfo/computer-go/ > >-- >This email has been verified as Virus free >Virus Protection and more available at http://www.plus.net ___ 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: 9x9 games wanted
It might be worth asking the administrators of some go servers if they would be prepared to give you copies of some games. At 17:09 06/07/2007, you wrote: I will play with Suzie at the forthcoming European Go championship in Villach/Austria some 9x9 demonstration matches against everybody who wants to play. I want to prepare an opening book and I am looking for a 9x9 games collection. So far I have only found in total 244 games, which is for a book much too less (I am used to have the CB-Megabase). Is there a larger collection with at least >= 5 Amateur Dan Level available? If the price is reasonable, I am willing to pay for a professionally made collection. Chrilly ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ -- This email has been verified as Virus free Virus Protection and more available at http://www.plus.net ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Re: 9x9 games wanted
Nici Schraudolph has some 9x9 human games; I think they include some Dan games, but I don't know how strong. Peter Drake http://www.lclark.edu/~drake/ On Jul 6, 2007, at 9:37 AM, Magnus Persson wrote: Quoting chrilly <[EMAIL PROTECTED]>: I will play with Suzie at the forthcoming European Go championship in Villach/Austria some 9x9 demonstration matches against everybody who wants to play. I want to prepare an opening book and I am looking for a 9x9 games collection. So far I have only found in total 244 games, which is for a book much too less (I am used to have the CB-Megabase). Is there a larger collection with at least >= 5 Amateur Dan Level available? If the price is reasonable, I am willing to pay for a professionally made collection. I am afraid that the best games you can get is probably games from high ranked programs on CGOS. As far as I know there are no serious collection of 9x9 Go except for what you already found. -Magnus ___ 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: 9x9 games wanted
Quoting chrilly <[EMAIL PROTECTED]>: I will play with Suzie at the forthcoming European Go championship in Villach/Austria some 9x9 demonstration matches against everybody who wants to play. I want to prepare an opening book and I am looking for a 9x9 games collection. So far I have only found in total 244 games, which is for a book much too less (I am used to have the CB-Megabase). Is there a larger collection with at least >= 5 Amateur Dan Level available? If the price is reasonable, I am willing to pay for a professionally made collection. I am afraid that the best games you can get is probably games from high ranked programs on CGOS. As far as I know there are no serious collection of 9x9 Go except for what you already found. -Magnus ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] Re: 9x9 games wanted
I will play with Suzie at the forthcoming European Go championship in Villach/Austria some 9x9 demonstration matches against everybody who wants to play. I want to prepare an opening book and I am looking for a 9x9 games collection. So far I have only found in total 244 games, which is for a book much too less (I am used to have the CB-Megabase). Is there a larger collection with at least >= 5 Amateur Dan Level available? If the price is reasonable, I am willing to pay for a professionally made collection. Chrilly ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] any problems with cgos 19x19 server?
I am seeing messages like this: 02:27:59Irrecgular response from server. Breaking connection. 02:27:59Connection to server has closed. Will try to reconnect shortly. Am restarting my 19x19 client. Anyone else having similar issues? 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 Pinpoint customers who are looking for what you sell. http://searchmarketing.yahoo.com/___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] Re: computer-go Digest, Vol 36, Issue 6
terry mcintyre wrote: Lately, I've been studying joseki, and I find that it's hard to really know a joseki until you know why non-joseki moves are bad - and why moves which are locally joseki may be bad in relation to other stones on the board. No doubt. That is the most complicated part. I have found nothing effective for that, although I have some ideas. Anyway, a program that "understands" joseki well enough to play each corner correctly even if not in relation with the other corners, is playing better than a program which does not understand joseki at all. Jacques. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Explanation to MoGo paper wanted.
Don Dailey wrote: For instance, in a set of master games what feedback do I have about each move other than that it was chosen? How do I get the opinion of the master player concerning the moves played and not played? Just an example: Search corner joseki sequences played often enough. Once you know where the player can play some alternative move (because you only learn "popular" sequences found in many games) or play tenuki (in this context, tenuki is a move outside the corner we are studying) _then_ use UCT simulations (measuring territory differences, not % of wins) to determine the temperature of each move by comparing the simulation with the move and the simulation with a pass instead. (Of course, not for passing, but for playing elsewhere). Your joseki database will have: the moves, their alternatives and the price you play for abandoning the sequence at a given point. Good style: In the case of good style, its is not really important to understand why good style is good. You will only study the move before the others, you won't necessarily play it. With limited time resources (i.e. always) studying good style moves before should give the program better style, but as the result of search (i.e. online knowledge). Again we integrate "human style" with what a computer understands. Far better, if you want to involve human players, is some kind of human assisted learning where games are played and learning takes place by trial and error and direct interaction with the "teacher." But this isn't very practical for machine learning which likes thousands of examples to work from. Here and in the rest of your post, I agree. We have to learn from strong players but we do not talk the same language ( unless they write programs, of course ;-) ). Their brain directs them to the good moves only. They filter bad moves so automatically, they don't realize that there are 250 stupid legal moves or more on a board and what consequences this has. Handcrafted databases are not a good idea for statistical analysis, but of course they have other good uses. E.g. not filling your own eyes is easily implemented as a handcrafted database. Jacques. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/