Re: [Computer-go] CGOS
Thanks a lot!!! I had the wrong adress, therefore I had trouble connecting the last weeks. cgos.computergo.org is the correct one, for some reason I had .net It seems to work for me, but I think you do not have reference bots running?! Therefore I do not get rating, even if I have two bots running?! Or did I miss anything?! Detlef Am Samstag, den 07.12.2013, 01:51 -0500 schrieb Joshua Shriver: Long story short... If you have ANY CGOS related questions, commentary, request... anything related to the server. Please feel free to msg the community, or email me directly at jshri...@gmail.com -Josh I'm new at this, I love and respect Don Dailey. Just hope I can at least feel 75% of his shoes, and make a difference. But I do have some nice and new ideas ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] A Regression test set for exploring some limitations of current MCTS programs in Go
Hi, I really put all my reading skills into case1.sgf of two_safe_groups. the test file says black to move, and I really can not get an answer for w to win against B J7 (and oakfoam does not too:). (by the way, the sgf says w to move) Could anybody please give me a hint Detlef Am Mittwoch, den 20.03.2013, 12:39 + schrieb Aja Huang: Dear all, If you are interested, you can download the newest version of our regression test set (seki and two-safe-groups) at http://webdocs.cs.ualberta.ca/~shihchie/seki-and-two-safe-groups-regression-test.zip or in Fuego svn http://fuego.svn.sourceforge.net/viewvc/fuego/trunk/regression/name which contains the results of all participating programs including Crazy Stone, Zen, Steenvreter, pachi, ManyFaces, Gomorra and Fuego, etc. Kind regards, Aja ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
[Computer-go] reusing engine instances in gomill and clop?
Hi, I wonder if anybody had the same problem. We have significant loading time of our go engine (oakfoam due to gamma loading). Both gomill and clop restart the engine for every compatition. In principle it should be possible to reuse the loaded instance? Did anybody try this? Thanks a lot Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
[Computer-go] Patch for Remi's original mm-tools
Hi,
I contacted Remi before, but he is using a much improved version of his
tools now and suggested I could share the patch here.
It speeds up the mm-tools by a factor of 50 in the iteration loop if you
use it for a high number of gammas (like in case of large patterns).
I hope it helps:)
This patch is minimalistic, so you should be able to check it's
correctness by reading. I have some more changes which allow the gcc
vectorizer to improve some of the initial loops, but this does not make
such a big difference.
Detlef
diff -rupN mm-orig/mm.cpp mm/mm.cpp
--- mm-orig/mm.cpp 2013-05-15 18:32:40.0 +0200
+++ mm/mm.cpp 2013-05-15 18:37:07.0 +0200
@@ -11,6 +11,7 @@
#include iomanip
#include sstream
#include vector
+#include map
#include cmath
#include fstream
@@ -180,13 +181,16 @@ void CGameCollection::MM(int Feature)
//
// Main loop over games
//
+ std::mapint,double tMul;
for (int i = vgame.size(); --i = 0;)
{
- double tMul[vGamma.size()];
- {
- for (int i = vGamma.size(); --i = 0;)
-tMul[i] = 0.0;
- }
+ //double tMul[vGamma.size()];
+ //{
+ // for (int i = vGamma.size(); --i = 0;)
+ // tMul[i] = 0.0;
+ //}
+ tMul.clear();
+
double Den = 0.0;
std::vectorCTeam v = vgame[i].vParticipants;
@@ -208,15 +212,25 @@ void CGameCollection::MM(int Feature)
if (FeatureIndex = 0)
{
-tMul[FeatureIndex] += Product;
+//tMul[FeatureIndex] += Product;
+if (tMul.count(FeatureIndex))
+ tMul[FeatureIndex] += Product;
+else
+ tMul[FeatureIndex]=Product;
+
Product *= vGamma[FeatureIndex];
}
Den += Product;
}
- for (int i = Max; --i = Min;)
- vDen[i] += tMul[i] / Den;
+ //for (int i = Max; --i = Min;)
+ // vDen[i] += tMul[i] / Den;
+ for (std::mapint,double::iterator it=tMul.begin();it!=tMul.end();++it)
+ {
+ int key=it-first;
+ vDen[key]+=it-second / Den;
+ }
}
//
___
Computer-go mailing list
Computer-go@dvandva.org
http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
[Computer-go] Computing Elo Ratings of Move Patterns in the Game of Go
Hi, I am struggling with one equation in this famous paper: http://remi.coulom.free.fr/Amsterdam2007/MMGoPatterns.pdf In section 2.2 the Bradley-Terry Model is generalized. The gammas are the playing strength, if I understood correctly. The first formula in the section scales quite nice: If one multiplies every playing strength by the same factor, the winning rate is not changed. But the second generalization does not scale any more? I do not understand, why this can be correct? Thanks for any help Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
[Computer-go] Effect of using large patterns in mc-tree
Hi, oakfoam was using large (circular) patterns (up to 9) in the last slow bot tournament. They were trained statistically. I read, that this is suboptimal and came up with an idea of another training: During play agains gnugo I compared for every move the order of move quality, which results from the features, with the one which results from mc calculation. My guess was: the features should try to produce the same order as the result from mc calculation. If I unprune in the order of the features this is good, as I unprune more or less in the order of the mc quality. After every move I change the values of all features in the better-fitting to mc order direction by a very little amount. As this seems to be stable for all features including 3x3 patterns it tries to remove most of my large patterns. I double checked for bugs, but of cause there might be some left. Did somebody try a similar approach? My understanding is: The large patterns do not improve the order. As they clearly improve the playing strength (100ELO for sure) there must be another reason, why they do it. My guess is: they introduce better tenukis into the tree to calculate different positions on the board. Therefore getting live and death better?! Or am I totally wrong and I should search very deep for a bug again:) Thanks Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] Congratulations to CrazyStone!
Can you provide a link to your thesis, as the one I found is dead:) Thanks Detlef Am Freitag, den 08.03.2013, 00:30 + schrieb Aja Huang: Now it seems to me that this is related to the way playouts are done and it will be difficult to improve with Mogo style (rule-based) playouts above certain strength, without using larger patterns and next move choice based on probability distribution. Currently, playing out a simple joseki in a sensible way in simulations will just never happen. This is a bit frustrating since all my attempts at successfully implementing probdist-based playouts have failed so far, but I guess I will just have to try again... To implement softmax, you can refer to my thesis where I have described the framework of the move generator for the playout. Detecting forbidden moves and replacing useless moves by better alternatives are very useful. There you can gain a lot by applying much Go-knowledge. Two good candidate algorithms for training the feature weights are MM and SB(Simulation Balancing). I tried hard but failed to measure any improvement from SB gammas (trained on 9x9) on 19x19. You can use CLOP to tune the MM gammas which are far from optimal according to our experience. Also, my regression test of seki and LD that pachi has participated could be helpful to improve program's tactical strength. In my opinion, that is the most crucial factor to reach high-dan level. Cheers, Aja ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] Japanese rules in KGS tournaments
If my version of the gtp protocol is the latest, there is no command for scoring (it is in the missing feature section). Should we try to extend the specification? Detlef Am Samstag, den 23.02.2013, 13:50 -0500 schrieb Don Dailey: Yes, it would be good to put the Japanese scoring to the test and nothing does this better than a tournament. Don On Sat, Feb 23, 2013 at 1:48 PM, Petr Baudis pa...@ucw.cz wrote: On Sat, Feb 23, 2013 at 07:37:35PM +0100, Erik van der Werf wrote: On Fri, Feb 22, 2013 at 5:18 AM, Martin Mueller mmuel...@ualberta.ca wrote: ... Do people consider this a solved problem? I do. BTW I think it would be nice to have some kgs tournaments with Japanese rules; good for testing, and it might even make 9x9 a bit more interesting... I second that idea. Having tournaments with Chinese rules by default is friendly to Computer Go beginners, but having a Japanese rules tournament once in a while would be nice to help weed out any bugs (and assess how often some corner cases actually happen :-), especially considering that some important non-KGS tournaments have Japanese rules. -- Petr Pasky Baudis For every complex problem there is an answer that is clear, simple, and wrong. -- H. L. Mencken ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
[Computer-go] Progressive Bias, progressive widening
Hi, I know, this topic was in the list a while ago. My problem is, as in all science, nobody publishes negative results:) Oakfoam uses both, progressive bias and progressive widening. My understanding is, this is state of the art in many mc bots, at least the theses I read used both. Both is working well in oakfoam. Now I turned off progressive widening and tuned progressive bias carefully (good scaling of the bias and improved decay functions). I got the same playing strength as with both (bias and widening) before on 9x9 against gnugo, but I can not improve anymore with progressive widening turned on again. My interpretation is: Progressive bias is the superior concept, but it is easier to use progressive widening. Progressive widening is not sensitive to the ratio of the pre knowledge value of two moves, only the better move must be unpruned first, but progressive bias is sensitive to the ratio between the pre knowledge values. It may be even more difficult to improve the progressive bias on 19x19, so there might be a reason to use widening, but at the moment I feel I should try without? Am I wrong? Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] Parallela and Computer Go
Hi! I saw this too, but the cores are ARM A9. With oakfoam one such core does 150 playouts / second on 19x19 (iPad1 with NiceGo, the free version of oakfoam for iPad), one i7-2600 core is more than 8 times faster. Even with good scaling a 64 core machine is only twice as fast as a i7-2600 I would think. Detlef m Mittwoch, den 24.10.2012, 11:15 +0200 schrieb Petr Baudis: Hi! There is a new fairly exciting parallelization platform in the works, currently as a kickstarter project (that will unfortunately likely not make it since while it's technically awesome, its marketing/PR campaign was far from stellar, but if you like it, don't hesitate to pledge in the next three days yet :) : http://www.kickstarter.com/projects/adapteva/parallella-a-supercomputer-for-everyone/ It consists of a control processor (in fact an FPGA) and a grid of 16 parallel processors in slightly Cell-like arrangement, with a promise to dramatically grow the number of processors in future. Single board costs $99. Something worth knowing about, I think - while the processors currently have fairly small amount of local memory, unfortunately, they still seem to me as much more suitable for Computer Go than GPUs as the thread on each parallel processor can be completely independent from others. Perhaps if the project makes it (on kickstarter or in another way), this is the hardware side of the next Computer Go strength boost to come. Petr Pasky Baudis ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] Congratulations to Zen!
Thanks Nick, your suggestion of adding the processor information is great. Would be good, if you add this to your http://www.weddslist.com/kgs/how/index.html information: than it should not be forgotten:) The problem with playing to the end is difficult I think. The things new computer go programmers have to take into account should not be too many and in short games it is no problem I think. Especially, as on cgos it is played this way, I would avoid to make it a must have?! But I do not think anybody would have a problem with you using your admin power! Detlef Am Samstag, den 15.09.2012, 16:53 +0100 schrieb Nick Wedd: Congratulations to Zen19S, winner of the Slow KGS bot tournament which ended ten days ago! My report is at http://www.weddslist.com/kgs/past/S12.2/index.html and I look forward, as usual, to receiving your comments and reports of errors. I apologise for the long delay in uploading this report. Nick ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
[Computer-go] KGS rank of Gnugo 3.8 Level 0
Hi, the subject tells it, does anybody ever run Gnugo3.8 Level 0 on KGS? I would be very interested in it's rank, thanks a lot Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] Sente Open Source Goban Application
As far as I read the web page there is no source of sente goban availible, they only offer the source of gnu go (because they must)?! Detlef Am Sonntag, den 26.08.2012, 19:33 +0300 schrieb James Watson: Hello All, I'm returning to Go after a long absence and have fond memories of playing Go using Sente's Goban (GNU Backend) on OSX (www.sente.ch/software/goban/). I've since returned to Linux and was wondering if anyone has had any success (or is currently working on) porting Goban to Linux? I have some Objective-C / Cocoa experience but none using GNUStep. Best regards jim ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] Congratulations to Zen!
Thanks a lot!! great tournament. stv was probably not running pachi (as you wrote in the hardware section:) As far as I know he runs on i7-3930.. Detlef Am Montag, den 13.08.2012, 11:11 +0100 schrieb Nick Wedd: Congratulations to Zen, winner of yesterday's bot tournament! My (very short) report is at http://www.weddslist.com/kgs/past/85/index.html As usual, I hope you will send me your corrections and comments. (One of you has already suggested that I use points instead of wins as a column header in the cross-table, because a jigo counts as half a point. But I prefer wins - I consider that a jigo is half a win, and there are many things (such as SOS) which could be described as points.) Nick ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] Kaś Cup - results and prizes
This is very interesting, I have not more than 10% with oakfoam on i7-2600K. Would be interesting if it is the processor or if you e.g. access more often memory instead of cache due to your code... Do you have the chance to run your program on a i7-2600? or do you have to much time and try https://bitbucket.org/francoisvn/oakfoam/wiki/Home on your i7-3930. If so, I would be very much interested in the number you get in the beginning of a 19x19 game without book:) Detlef Am Donnerstag, den 09.08.2012, 12:16 +0200 schrieb Erik van der Werf: On Thu, Aug 9, 2012 at 11:14 AM, Petr Baudis pa...@ucw.cz wrote: On Wed, Aug 08, 2012 at 09:08:47PM +0200, ds wrote: Hyperthreading does the trick, I have the experience it increases the performance by about 10%. I think this is due to waiting for RAM I/O or things like that Yes. With hyperthreading, performance per thread goes down significantly, but total performance goes up by about 15%. In the Pentium 4 era, hyperthreading did not usually pay off, but with i7, its performance is much better. The basic idea is that there are two instruction pipelines that share the same ALU and other processor units; if one of the pipelines stalls (usually due to memory fetch), the other can use the ALU in the meantime, or the two threads may use different parts of the CPU altogether based on what the instructions do. 10-15%, really, that low? For my program (on an i7-3930K, going from 6 to 12 threads) it is more in the order of 40% extra simulations per second. Erik ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] Kaś Cup - results and prizes
Hyperthreading does the trick, I have the experience it increases the performance by about 10%. I think this is due to waiting for RAM I/O or things like that Detlef Am Mittwoch, den 08.08.2012, 10:21 -0700 schrieb Richard Lorentz: This surprises me. Isn't it inefficient to have one core run multiple-threads? Can you explain why you did it this way to a hardware challenged person like me. Thanks. On 08/07/2012 03:35 AM, Petr Baudis wrote: Program authors / operators, please state in this thread the hardware used. Intel(R) Core(TM) i7-2600 CPU @ 3.40GHz. It seems it is auto-overlocked to 3.7GHz. Four cores, eight threads. ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] GnuGo failing unexpectedly
Hi, I had similar problems on some hardware (e.g. mac mini). I was not sure if it was due to a hardware problem I had with this computer. If I see, that this happens not to frequently I just edit the lines in the GoGui.py to ignore the error Detlef Am Montag, den 30.07.2012, 13:27 -0700 schrieb Samuel Stewart: Hello all, My name is Sam Stewart and I'm a student working with a research group developing a Go AI. Recently, I have been utilizing CLOP (an optimization system) to tune several parameters in our program. CLOP employs the twogtp bridge, packaged with GoGui, along with the gogui-adapter. CLOP managed to run about 1,000 games before the twogtp bridge failed with the message: The Go program terminated unexpectedly After searching through the logs (attached) it appears that GnuGo failed to generate a response to white. The twogtp bridge then forced white to quit (our program, Orego) and calculated the final score. While the error is regrettably vague, I'm curious if anyone has had trouble with the twogtp + GnuGo combination in the past? I welcome any suggestions for further debugging/fixes. Note: I have also attached the complete *.sgf file of the game. Thanks, Sam Stewart ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] Effect of lgrf on the playing strength agains gnugo
Thanks a lot, makes me feel much better:) Do you have no learning left in the playout than? Detlef Am Freitag, den 15.06.2012, 13:51 +0200 schrieb Petr Baudis: Hi! On Thu, Jun 14, 2012 at 07:47:41AM +0200, ds wrote: as answers here are always very helpful, my problem: We (oakfoam) have a small number of playout rules: last atari, last 2 liberty atari, patterns, fill board (mogo like I think) and a capture heuristic (more or less in this order). Playing (1000 playouts/move) against gnugo (3.8l10) we play around even but I can not measure any (positive) effect of last good reply rules (which I checked a number of times and which do have positive effect on special board situations like seki). Similar problems I have trying pool rave rules. Does anybody have similar problems? In Pachi, we couldn't make it to work either. I think that as always, it's a heuristic whose effect highly matters on your current mix and might be made redundant by something else you do. Petr Pasky Baudis ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
[Computer-go] Effect of lgrf on the playing strength agains gnugo
Hi, as answers here are always very helpful, my problem: We (oakfoam) have a small number of playout rules: last atari, last 2 liberty atari, patterns, fill board (mogo like I think) and a capture heuristic (more or less in this order). Playing (1000 playouts/move) against gnugo (3.8l10) we play around even but I can not measure any (positive) effect of last good reply rules (which I checked a number of times and which do have positive effect on special board situations like seki). Similar problems I have trying pool rave rules. Does anybody have similar problems? Thanks a lot Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
[Computer-go] Young Sun Yoon 8p discussed Takemiya v.s. Zen on KGSplus
Hi, I ask her to discuss it and she did. It is a Audio Lecture of 83min in English discussing the 4 handicap game. Quite interesting, but only for KGSplus members. As we all profit from KGS it might be acceptable to donate 3 month of kgsplus (15$ or so). Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] May KGS bot tournament: full-size boards
I think it is now 701... (changed during editing I think) Am Mittwoch, den 02.05.2012, 14:13 -0700 schrieb Peter Drake: I'm still getting a 404 on this. Is 700 the right number? On Apr 26, 2012, at 12:14 PM, Nick Wedd wrote: The May KGS bot tournament will be held on Sunday May 6th, starting at 16:00 UTC and finishing at 22:00. It will be an 12-round Swiss with 19x19 boards and 14 minutes each, plus fast Canadian overtime. It will use Chinese rules with 7.5 points komi. There are details at http://www.gokgs.com/tournInfo.jsp?id=700 . Please send your registration email, with the words KGS Tournament Registration in the title, to me at maproom at gmail dot com (converted to a valid address by using @ and .). Nick -- Nick Wedd n...@maproom.co.uk ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go Peter Drake http://www.lclark.edu/~drake/ ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] May KGS bot tournament: full-size boards
hi, in kgs description is said, that this is a handicap tournament. This is probably an error? Am Donnerstag, den 26.04.2012, 20:14 +0100 schrieb Nick Wedd: The May KGS bot tournament will be held on Sunday May 6th, starting at 16:00 UTC and finishing at 22:00. It will be an 12-round Swiss with 19x19 boards and 14 minutes each, plus fast Canadian overtime. It will use Chinese rules with 7.5 points komi. There are details at http://www.gokgs.com/tournInfo.jsp?id=700 . Please send your registration email, with the words KGS Tournament Registration in the title, to me at maproom at gmail dot com (converted to a valid address by using @ and .). Nick ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] cgos
Sorry, I do not want to get all your secrets, but how do you do 250k playouts with seconds for a whole game on all boardsize with 4 cores? Or does reservation mean a minimum reservation? Detlef Am Dienstag, den 24.04.2012, 12:40 +0200 schrieb Rémi Coulom: I reserved a small 4-core node of our cluster to connect 9 fast instances of Crazy Stone, 3 for each board size. On 23 avr. 2012, at 19:48, ds wrote: Hi, would be nice, if one could arrange a typical date, where one can hope to find more programs on cgos. E.g. once a week or once every two weeks on monday? Depending on the opponents one could let the programs run for some hours or some days. For the last weeks it was quite empty with only the standard programs running. You can only get rated around 1800ELO with some accuracy... Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] cgos
Thanks a lot, there is a long way to go for us with this impressible strength:) Detlef Am Dienstag, den 24.04.2012, 19:43 +0200 schrieb Rémi Coulom: In Crazy Stone, I set the total number of playouts per game, not per move. 250k per game is similar in strength to 2k playouts per move (a bit weaker, maybe). But it takes less time overall for one game (because I apply time-management heuristics to playouts), which allows faster testing. Rémi On 24 avr. 2012, at 18:38, ds wrote: Sorry, I do not want to get all your secrets, but how do you do 250k playouts with seconds for a whole game on all boardsize with 4 cores? Or does reservation mean a minimum reservation? Detlef Am Dienstag, den 24.04.2012, 12:40 +0200 schrieb Rémi Coulom: I reserved a small 4-core node of our cluster to connect 9 fast instances of Crazy Stone, 3 for each board size. On 23 avr. 2012, at 19:48, ds wrote: Hi, would be nice, if one could arrange a typical date, where one can hope to find more programs on cgos. E.g. once a week or once every two weeks on monday? Depending on the opponents one could let the programs run for some hours or some days. For the last weeks it was quite empty with only the standard programs running. You can only get rated around 1800ELO with some accuracy... Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
[Computer-go] cgos
Hi, would be nice, if one could arrange a typical date, where one can hope to find more programs on cgos. E.g. once a week or once every two weeks on monday? Depending on the opponents one could let the programs run for some hours or some days. For the last weeks it was quite empty with only the standard programs running. You can only get rated around 1800ELO with some accuracy... Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] cgos
Am Montag, den 23.04.2012, 13:55 -0400 schrieb Joshua Shriver: That's kinda what I'm doing now. I have a quad Xeon running 3 copies of gnugo, 9, 13 and 19. Hope it's been useful. I just built a 6core machine with 8gigs of memory for ~$550 US. So these beasts are getting cheap. Thats kind of interesting, I do not even have a 6core for playing oakfoam at the moment. I did some research, but could only find a i7-2600 for that price (incl. taxes in germany)? What machine are you building? Detlef -Josh On Mon, Apr 23, 2012 at 1:53 PM, Don Dailey dailey@gmail.com wrote: I have always wished that we could keep a range of programs with different strengths always playing, but that requires computer resources. If I was wealthy I would donate a 6 core machine solely for this purpose - but I am not :-) A single machine with a few cores could keep a few programs always on-line ready to play. Don On Mon, Apr 23, 2012 at 1:48 PM, ds d...@physik.de wrote: Hi, would be nice, if one could arrange a typical date, where one can hope to find more programs on cgos. E.g. once a week or once every two weeks on monday? Depending on the opponents one could let the programs run for some hours or some days. For the last weeks it was quite empty with only the standard programs running. You can only get rated around 1800ELO with some accuracy... Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] cgos
Thanks a lot for the reply, from the benchmarks I found the 4 core i7-2600 is a little faster http://www.cpubenchmark.net/cpu.php?cpu=AMD+FX-8120+Eight-Core Hopefully it gets a little cheaper now, that the eve bridge processors are comming:) Detlef Am Montag, den 23.04.2012, 14:08 -0400 schrieb Joshua Shriver: Bought the pieces from a local mom-pop shop that has great pricing. AMD Phenom II x6 core 179 Asus M4A89GTD-Pro AM3 motherboard 179 DDR3 4gig memory x2 $35 a piece. Antec case and Corsair 500w PSU 119 Already had a hard drive to use so that saved me ~$100. -Josh On Mon, Apr 23, 2012 at 2:02 PM, ds d...@physik.de wrote: Am Montag, den 23.04.2012, 13:55 -0400 schrieb Joshua Shriver: That's kinda what I'm doing now. I have a quad Xeon running 3 copies of gnugo, 9, 13 and 19. Hope it's been useful. I just built a 6core machine with 8gigs of memory for ~$550 US. So these beasts are getting cheap. Thats kind of interesting, I do not even have a 6core for playing oakfoam at the moment. I did some research, but could only find a i7-2600 for that price (incl. taxes in germany)? What machine are you building? Detlef -Josh On Mon, Apr 23, 2012 at 1:53 PM, Don Dailey dailey@gmail.com wrote: I have always wished that we could keep a range of programs with different strengths always playing, but that requires computer resources. If I was wealthy I would donate a 6 core machine solely for this purpose - but I am not :-) A single machine with a few cores could keep a few programs always on-line ready to play. Don On Mon, Apr 23, 2012 at 1:48 PM, ds d...@physik.de wrote: Hi, would be nice, if one could arrange a typical date, where one can hope to find more programs on cgos. E.g. once a week or once every two weeks on monday? Depending on the opponents one could let the programs run for some hours or some days. For the last weeks it was quite empty with only the standard programs running. You can only get rated around 1800ELO with some accuracy... Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] useless ko threats
Am Dienstag, den 06.03.2012, 15:35 + schrieb Matthew Woodcraft: Stefan Kaitschick wrote: Bots love to throw in useless ko threat type moves now and then. Sometimes its just a wasted threat, at other times it loses a useful liberty too. Why do even strong bots show this stupid behaviour? Ko threat type moves have one thing in common: a big payoff if the opponent answers incorrectly. If the first response tested is wrong, then the ko threat will start off with a very good winrate. The correct response will be found fairly soon, but by then the original move will have a winrate bonus. This bonus is small, but it is there. The problem is, that the winrate degradation, that a useless ko threat causes, can also be small. So if the (erroneous) bonus outweighs the (real) loss, the bot will conclude that throwing in the ko threat is good. I think it's a little more complicated than that. Suppose that X and Y are a ko threat and its only response, and A is the 'best' move (the move that the computer would play if the ko threat wasn't an option). Then X is competing against A. X has a (large) advantage for each time the 'opponent' fails to choose Y, but it also has a disadvantage for each time the 'player' chooses a move other than A in the position after X-Y. The problem is even worse: if the playout does not handle using ko threads, X would (most of the time) not have any disadvantage at all... -M- ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] KGS Rating Drift
This is an interesting observation. They even drift without playing (NiceGo played last time on 18.2. and increased half a rank since than...) Detlef Am Mittwoch, den 29.02.2012, 15:12 +0100 schrieb Petr Baudis: Hi! Just a word of warning - in the last two or three weeks, all ranks on KGS (at least ranks of all programs) started experiencing a strong upwards rating drift (by up to half a rank so far), so be careful about misinterpreting impact of any recent changes if you use KGS rating for evaluation. P.S.: I have warned the admins about this but got no reply so far. Perhaps to limit abuse, it would be wise to rate-limit impact of games against programs on rating to two games per week for each user (in some smart stochastic way). Happy coding, ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] Elastic Cloud
I wonder if this instance should not have 16 cores? I read the german translation of amazon, and this sounds as if there are two 8 core xeons? Thanks Detlef Am Mittwoch, den 14.12.2011, 16:00 -1000 schrieb Mark Boon: On Wed, Dec 7, 2011 at 8:28 PM, Aja Huang ajahu...@gmail.com wrote: In the UEC Cup last weekend, I rented a machine from Amazon EC2 to run Erica: High-CPU Extra Large Windows Instance (c1.xlarge) $1.16 per/hour (High-CPU Extra Large Instance 7 GB of memory, 20 EC2 Compute Units (8 virtual cores with 2.5 EC2 Compute Units each), 1690 GB of local instance storage, 64-bit platform) However, according to my testing, this machine is around 1.5 times slower than my 4-core (i7 950) PC. It is a high-level instance aleady but actually very slow. A competition on equal hardware from Amazon EC2 might be interesting, but such weak hardware might not reflect program's performance on large simulations. Just now I ran a short test on a new instance type that became available on Amazon today. These are the specs from their web-site: 60.5 GB of memory 88 EC2 Compute Units (eight-core 2 x Intel Xeon) 3370 GB of instance storage 64-bit platform I/O Performance: Very High (10 Gigabit Ethernet) API name: cc2.8xlarge Cost: $2.40/h Running my little Java benchmark showed the highest number of playouts using 8 threads, ~155 Kpps. That compares rather poorly to my 4 year old MacPro that does ~240 Kpps. So indeed not as hot as you might believe at first from the specs. Mark ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] Beating old ManyFaces at 29 handicap stones
Should be no trouble with the rating system, it seems that you did not register mfgo1998 as rated bot. So all games should be free. Am Sonntag, den 29.01.2012, 08:59 -0800 schrieb David Fotland: please do not set handicaps just by passing, start with at least 6 handicap, then pass. If you set handicap to 6 or more the game will be free. Otherwise kgs treats it as a rated game, without handicap and it will mess up the raking system. mfgo1998 expects a 9 stone handicap then many passes to get to 29 stones. Otherwise its own internal handicap concept will be incorrect. David -Original Message- From: computer-go-boun...@dvandva.org [mailto:computer-go- boun...@dvandva.org] On Behalf Of Hiroshi Yamashita Sent: Sunday, January 29, 2012 2:01 AM To: computer-go@dvandva.org Subject: Re: [Computer-go] Beating old ManyFaces at 29 handicap stones Thanks! Aya tried 6 games. Aya uses 2 cores, 10sec/move. I think 14 handicaps is best for Aya. handicaps 5 win 11 win 9 win 16 loss 14 loss 14 win http://www.gokgs.com/gameArchives.jsp?user=ayamc Some small problem. I don't know how to select B, and set 9 handicap on KgsGtp. So I just passed 14 times in 14 hadicaps game, but KGS set komi to 6.5, and does not minus handicaps stones in final result. My config file is like this. --- engine=c:/go/kgs/AyaMC/aya.exe firstargument=--mode gtp verbose=f server.host=goserver.gokgs.com server.port=2379 name=AyaMC password=** room=Computer Go #mode=custom mode=wait talk=Good evening. I am a bot and do not talk. gameNotes=monte-carlo based Aya opponent=mfgo1998 rules=chinese rules.boardSize=19 rules.time=10:00+5x0:30 reconnect=t --- Hiroshi Yamashita - Original Message - From: David Fotland fotl...@smart-games.com To: computer-go@dvandva.org Sent: Sunday, January 29, 2012 10:33 AM Subject: Re: [Computer-go] Beating old ManyFaces at 29 handicap stones mfgo1998 is up on kgs if anyone wants to try it. To get a big handicap, set up a 9 stone game and pass until you get up to 29 stones in the same pattern as Martin's game. Regards, David -Original Message- From: computer-go-boun...@dvandva.org [mailto:computer-go- boun...@dvandva.org] On Behalf Of David Fotland Sent: Saturday, January 28, 2012 11:34 AM To: computer-go@dvandva.org Subject: Re: [Computer-go] Beating old ManyFaces at 29 handicap stones The game with Martin was played on 8/5/1998 at the US Go Congress. My closest source is dated 7/3/1998. I have this built into a gtp front end now, and it's playing different moves from Martin's game, so the engine is not identical. Do you still want to continue with this bet? David -Original Message- From: computer-go-boun...@dvandva.org [mailto:computer-go- boun...@dvandva.org] On Behalf Of Ingo Althöfer Sent: Thursday, January 26, 2012 1:22 PM To: computer-go@dvandva.org Subject: Re: [Computer-go] Beating old ManyFaces at 29 handicap stones Which old Manyface, I have a DOS version from 1990 :) In 1997 ManyFaces 10.0 came to the market (and is sol still nowadays). David Fotland wrote that in the game against Martin Mueller he likely used a source from July 1998. He will try to reanimate that. ingo. -- Empfehlen Sie GMX DSL Ihren Freunden und Bekannten und wir belohnen Sie mit bis zu 50,- Euro! https://freundschaftswerbung.gmx.de ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] Beating old ManyFaces at 29 handicap stones
I unpacked my nice packed version from 1991 again, but it seems that it does not implement even the go modem protocol. At least it is not in the printed (!) user manual:) If somebody knows more, I would let my version play on KGS. This should not make it to easy to tune for the 1999 version, but to get an idea how to play a weak opponent. Detlef Am Freitag, den 27.01.2012, 16:50 +0100 schrieb Stefan Kaitschick: Of course, for experiments it would be neat to have a binary of this version, but maybe that would make the challenge too easy (or prone to overtuning). My guess is, that opponent modeling will have to be part of the package. For a generic weak opponent, maybe one sided simulation balancing would work. But it may very well be necessary to specifically model the opponents weaknesses. I hope that this version of MF is non-deterministic. :-) Stefan ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
[Computer-go] KGS, gogui and handicap stones
Hi, sounds simple, but I could not figure out: If I load a game from kgs with gogui, my engine is not informed about the handicap stones. Therefore it counts wrong? Is there a workaround? Thanks Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
[Computer-go] CLOP and BOOL Parameters
Hello, I had a first look at CLOP and it seems really easy to use. Great! One question arises: Can I add bool Parameters, e.g. to enable playout features or must I change them by hand? Thanks a lot Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] CrazyStone in the 5-dan footsteps of Zen
The can take place in the auto pairing and choose some of the criteria as far as I know. Am Dienstag, den 03.01.2012, 16:02 + schrieb Nick Wedd: On 03/01/2012 15:19, terry mcintyre wrote: Does KGS support the ability to challenge a specific opponent? Yes. Could computer programs respond to such challenges, modulo specific criteria such as player rank, games per period, notoriety, etc? Bots playing on KGS cannot, I believe, accept existing challenges. Nick Terry McIntyre terrymcint...@yahoo.com Unix/Linux Systems Administration ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] another Shodan Challenge?
The account on kgs Liisa has this X-Price text in the info. Am Dienstag, den 14.06.2011, 03:53 +0200 schrieb Ingo Althöfer: Thanks to Willemien to bring up this information. Original-Nachricht on http://www.suomigo.net/wiki/JouniValkonen There is another challenge: X-Prize# If someone makes a gobot that wins me on best of 5 match (80 40 fischer), I will pay for the programmer €1000 X-prize. Prize will be in effect for the next 2000 years or when the winner of the competition has been found. Challenges can be played during European Go Congress, but I accept them only after successful preliminaries played on rapid time settings at KGS. ... Some questions and comments from my side: * which rules: chinese? * best of five is clear for me, but what means 80 40 fischer? Is it 80 minutes base time + 40 seconds increment for each move played? * Will the bot be allowed to play with remote hardware? * European Go Congress 2011 is in Bordeaux: July 23 to August 06. There is a very strong french bot around. Remi might find sponsors who back him with 1,000 Euro. * European Go Congress 2012 will be in Bonn (Germany): July 21 to August 04. There should be German sponsors to back a programmer with 1,000 Euro. * Which account is Jouni on KGS now? Ingo. ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] kgsGtp update required!
Thanks for the information. I updated yesterday, and on the page was 3.4.15 :-) One short question: In http://www.weddslist.com/kgs/how/tourney.html you mention open=f but it is not in the sample file for tournament. Is it recommanded? Thanks Detlef Am Sonntag, den 22.05.2011, 09:11 +0200 schrieb Petr Baudis: Hi! Beware especially for participants of today tournament - kgsGtp update is required because of nonbackwardscompatible KGS version change tonight: http://files.gokgs.com/changeLog.txt With old kgsGtp, you will see immediate disconnects from server with no further explanation. You can get new kgsGtp version at http://files.gokgs.com/javaBin/kgsGtp-3.5.0.tar.gz http://files.gokgs.com/javaBin/kgsGtp-3.5.0.zip If like me, you have not updated kgsGtp for a while, you might be interested to know that it now supports mode=both to enable both automatch and challenge wait, you can prevent handicap automatch games if you do not support the handicap command, and you can get information about current ruleset used by the kgs-rules command. ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] May KGS bot tournament: 19x19, fast
When registering for the tournament you ask for a lot of information. Send an email to the organiser, with the words KGS Tournament Registration in the title, stating: * The name of your bot, as registered on KGS * The real name of your bot, if different * The names of the authors of all parts of your Go-playing program. I will expect you to have the consent of all these people for your program to be entered in this tournament. * the processor power (number of processors, and processor speed) of the platform that it will be running on * (if entering the formal division) your own name. I may request evidence of this. Are they kept secret, as they might be quite interesting?! E.G. One would know, if the basis of a bot is GPL ... Thanks a lot Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] May KGS bot tournament: 19x19, fast
Thank you very much for the information: I had difficulties to find the reports:-) Now I found them. Small question: Do you have an sample gks configuration for a bot to take place at an tournment? The standard file would let other players allow to challenge the bot during tournment?! Thanks once again Detlef Am Montag, den 09.05.2011, 15:00 +0100 schrieb Nick Wedd: In message 1304947990.22771.4.camel@laptop, ds d...@physik.de writes When registering for the tournament you ask for a lot of information. Send an email to the organiser, with the words KGS Tournament Registration in the title, stating: * The name of your bot, as registered on KGS I need this to register it for the tournament * The real name of your bot, if different I use this at http://www.computer-go.info/db/oproglist.php * The names of the authors of all parts of your Go-playing program. I will expect you to have the consent of all these people for your program to be entered in this tournament. I want to ensure that the program is its owner's own work. In particular, I do not want multiple copies of GNU Go. * the processor power (number of processors, and processor speed) of the platform that it will be running on This information is listed at the bottom of my reports. * (if entering the formal division) your own name. I may request evidence of this. This is obsolete, I ought to delete it. Nick Are they kept secret, as they might be quite interesting?! E.G. One would know, if the basis of a bot is GPL ... Thanks a lot Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
[Computer-go] MC Beginner question
If I read correctly, the playout results in Monte Carlo usually used are only win or loss. Is there a good reason, why one should not take into account height (number of stones) of the win? It feels like loosing information to me?! Thanks a lot Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
Re: [Computer-go] MC Beginner question
Yes thanks for the answer. It is difficult to search the list for detailed information. Do you know, if anybody tried an approach as dynamic Komi with this. In the beginning of the game take into account the stones (eg. sqrt(sones) and reduce it later. In the beginning an estimated high win should be probably more save than a 0.5 win?! Thanks Detlef Am Freitag, den 29.04.2011, 12:21 +0200 schrieb Oliver Lewis: This has been the subject of many discussions and debates on this list. Essentially, the evidence shows that although win/loss loses information, it is the most correct evaluation that captures what the go player should try to achieve. If you take into account the size of the win, you are somehow saying that bigger wins are better than small wins. However you weight the scores, you risk the programme favouring some of the aggressive lines of attack which may also be riskier, rather than playing safe for a half-point win. On Fri, Apr 29, 2011 at 11:15 AM, ds d...@physik.de wrote: If I read correctly, the playout results in Monte Carlo usually used are only win or loss. Is there a good reason, why one should not take into account height (number of stones) of the win? It feels like loosing information to me?! Thanks a lot Detlef ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
