Search found 90 matches

by jonkr
Sat Nov 21, 2020 9:19 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: First success with neural nets
Replies: 30
Views: 5859

Re: First success with neural nets

I updated the code. Refactored a lot of it to try to make it easier to use in multiple different games and have some more standard search features and faster neural net calculation. GuiNN 2.04 against GuiCheckers 1.11 (an old pre-NN version) at .2s per-move 1169-31-1680 W-L-D (+145 elo) Which is pre...
by jonkr
Thu Nov 19, 2020 9:03 pm
Forum: Computer Chess Club: Tournaments and Matches
Topic: FGRL, 60 sec + 0.6 sec - 2. Dragon by Komodo Chess 1.0, 7. Komodo 14.1 MCTS, 10. SlowChess Blitz Classic 2.4
Replies: 12
Views: 1008

Re: FGRL, 60 sec + 0.6 sec - 2. Dragon by Komodo Chess 1.0, 7. Komodo 14.1 MCTS, 10. SlowChess Blitz Classic 2.4

Thanks for re-testing, at least it inched in the right direction this time. Hopefully will make more difference against stronger opponents.
2.4 is mostly just 2.3 with the endgame nets added. (I guess maybe had worse luck than 2.3 first test.)
by jonkr
Wed Nov 18, 2020 9:04 pm
Forum: Computer Chess Club: Tournaments and Matches
Topic: SlowChess Blitz Classic 2.3 64-bit 4CPU Gauntlet CCRL 40/15
Replies: 2
Views: 99

Re: SlowChess Blitz Classic 2.3 64-bit 4CPU Gauntlet CCRL 40/15

Thanks for testing SlowChess 4CPU. When I re-started work on it I never expected to see it top 5 overall in the CCRL list.
(I expect position will start to drop now but it was a good run.)
by jonkr
Wed Nov 18, 2020 8:50 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: First success with neural nets
Replies: 30
Views: 5859

Re: First success with neural nets

I will probably try it out sometime this week in the checkers program and see if it seems worth it. It is more state to track, and the speed up is unlikely to be that big, but I expect could find a clear speedup for early/mid game. (To compute the first first layer values, currently the Checkers net...
by jonkr
Sat Nov 14, 2020 10:43 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: First success with neural nets
Replies: 30
Views: 5859

Re: First success with neural nets

This is really amazing! I've managed to both compile your engine and run your Python training code, it all works flawlessly. I have a GTX 1050 Ti with 4Gb RAM as GPU and that allows me to use a batch size of 1M (instead of your 15K). All the other parameter (learning schedule) I left untouched. Tra...
by jonkr
Sat Nov 14, 2020 10:26 pm
Forum: Computer Chess Club: Tournaments and Matches
Topic: FGRL, 60 sec + 0.6 sec - 2. Dragon by Komodo Chess 1.0, 7. Komodo 14.1 MCTS, 10. SlowChess Blitz Classic 2.4
Replies: 12
Views: 1008

Re: FGRL, 60 sec + 0.6 sec - 2. Dragon by Komodo Chess 1.0, 7. Komodo 14.1 MCTS, 10. SlowChess Blitz Classic 2.4

The result with Slow 2.4 slightly below 2.3 and 2.2 does come as a surprise even knowing the gains might not show up so much against weaker opponents. In SPCC and in the CEGT forum I see a 20+ elo gain for 2.4 vs 2.3, and versus the older 2.2 I got +42 elo standard, +51 FRC in my own testing. Not ha...
by jonkr
Fri Nov 13, 2020 7:29 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: First success with neural nets
Replies: 30
Views: 5859

Re: First success with neural nets

While cleaning up the GuiNN checkers code some more I managed to improve it by an extra 10 elo. So it definitely has some room to grow but maybe I am done now since checkers could be mostly covered by large databases instead, and not using them feels a bit artificial. International Draughts is an in...
by jonkr
Thu Nov 12, 2020 12:13 am
Forum: Computer Chess Club: Tournaments and Matches
Topic: My test for SlowChess Blitz Classic 2.4 x64
Replies: 4
Views: 385

Re: My test for SlowChess Blitz Classic 2.4 x64

Thanks for testing, tough second half for SlowChess. This is the first time I've seen someone use the own book in a match. I should start updating it again, I stopped around 1.8. I used to run 2min+1s matches with release candidates, and have it learn the first 13 moves of winning/drawing side(s). R...
by jonkr
Wed Nov 11, 2020 11:59 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: First success with neural nets
Replies: 30
Views: 5859

Re: First success with neural nets

Despite not working on chess, I have still been testing out neural nets. I started first with something very similar : Checkers. 15-20 years ago I had worked a bit on a checkers program. Using the same neural net code and training method I had used for chess endgames and detailed in this thread, I w...
by jonkr
Sat Nov 07, 2020 8:24 pm
Forum: Computer Chess Club: Tournaments and Matches
Topic: SPCC: Testrun of Slow Chess 2.4 finished
Replies: 1
Views: 219

Re: SPCC: Testrun of Slow Chess 2.4 finished

Thanks for testing, +23 elo is slightly above my +21 self-play elo gain so I'm pretty happy with that result in a general rating list.
Probably/hopefully that means the endgame neural net learning scales better than some general gains do. (My testing was at 15s +.15)