It seems to me, that the whole CCC forum is waiting for LC0 to pass Stockfish finally,
so how many of you programmers are working on neural networks for chess?
Myself still ponders on how to combine an AlphaBeta searcher with gpgpu ann eval...
--
Srdja
So, how many of you are working on neural networks for chess?
Moderators: hgm, Rebel, chrisw
-
- Posts: 2724
- Joined: Wed Mar 10, 2010 10:18 pm
- Location: Hamburg, Germany
- Full name: Srdja Matovic
-
- Posts: 558
- Joined: Sat Mar 25, 2006 8:27 pm
Re: So, how many of you are working on neural networks for chess?
I have to wait until I can get a new computer first. But, hopefully this summer.
-
- Posts: 931
- Joined: Tue Mar 09, 2010 3:46 pm
- Location: New York
- Full name: Álvaro Begué (RuyDos)
-
- Posts: 4185
- Joined: Tue Mar 14, 2006 11:34 am
- Location: Ethiopia
Re: So, how many of you are working on neural networks for chess?
Watch it you don't who might be surfing the webAlvaroBegue wrote: ↑Sat Feb 02, 2019 12:22 amI have a promising idea for that, but I don't really have the time to implement it. My job, my wife and my kids are getting in the way of the really important stuff!
-
- Posts: 363
- Joined: Thu Jan 22, 2015 3:21 pm
- Location: Zurich, Switzerland
- Full name: Jonathan Rosenthal
Re: So, how many of you are working on neural networks for chess?
One of the main reasons I am not working on an NN based engine is that I feel I don't have the resources. I think very few people have the resources to seriously train and test a NN based engine.
Reinforcement learning based NN engines are even worse in that regard.
I don't understand how it matters whether Leela or SF is stonger. Depends on the conditions anyways.
Reinforcement learning based NN engines are even worse in that regard.
I don't understand how it matters whether Leela or SF is stonger. Depends on the conditions anyways.
-Jonathan
-
- Posts: 4368
- Joined: Fri Mar 10, 2006 5:23 am
- Location: http://www.arasanchess.org
Re: So, how many of you are working on neural networks for chess?
I think still NN engines even on higher-end commercial graphics cards play blunders at a pretty high rate.
I think there is probably room for a hybrid approach where maybe the NN is suggesting moves to a deep searcher, but I am not aware of anyone pursuing that.
Personally I have a pretty long to-do list for my non-NN engine and I am not planning to drop everything and start building a NN.
--Jon
I think there is probably room for a hybrid approach where maybe the NN is suggesting moves to a deep searcher, but I am not aware of anyone pursuing that.
Personally I have a pretty long to-do list for my non-NN engine and I am not planning to drop everything and start building a NN.
--Jon
-
- Posts: 536
- Joined: Thu Mar 09, 2006 3:01 pm
Re: So, how many of you are working on neural networks for chess?
My resources include a 2 year-old GTX 1070 GPU. With that I was able to train (supervised learning) a 10x128 Leela net from the "standard CCRL" dataset (link below). It took about a week, and it is competitive with Crafty on between 2 and 4 CPUs, so about 2,900 Elo. It is not as serious as the larger Leela project, but has been quite rewarding learning enough to do it.jorose wrote: ↑Sat Feb 02, 2019 12:50 am One of the main reasons I am not working on an NN based engine is that I feel I don't have the resources. I think very few people have the resources to seriously train and test a NN based engine.
Reinforcement learning based NN engines are even worse in that regard.
I don't understand how it matters whether Leela or SF is stonger. Depends on the conditions anyways.
http://blog.lczero.org/2018/09/a-standard-dataset.html
-
- Posts: 4185
- Joined: Tue Mar 14, 2006 11:34 am
- Location: Ethiopia
Re: So, how many of you are working on neural networks for chess?
My NN engine never makes a blunder because I spend 20% of the time doing a mulitpv search calculating scores for root moves,jdart wrote: ↑Sat Feb 02, 2019 3:41 am I think still NN engines even on higher-end commercial graphics cards play blunders at a pretty high rate.
I think there is probably room for a hybrid approach where maybe the NN is suggesting moves to a deep searcher, but I am not aware of anyone pursuing that.
Personally I have a pretty long to-do list for my non-NN engine and I am not planning to drop everything and start building a NN.
--Jon
and then combining that with MCTS scores like: 0.2 * ABscore + 0.8 * MCTSscore. That way the selection of moves at the root is biased
by the alphabeta prior score and that makes it avoid almost all blunders.
-
- Posts: 7221
- Joined: Mon May 27, 2013 10:31 am
Re: So, how many of you are working on neural networks for chess?
NN = far too slow = black box = useless
-
- Posts: 363
- Joined: Thu Jan 22, 2015 3:21 pm
- Location: Zurich, Switzerland
- Full name: Jonathan Rosenthal
Re: So, how many of you are working on neural networks for chess?
How is ScorpioNN coming along?Daniel Shawul wrote: ↑Sat Feb 02, 2019 7:00 amMy NN engine never makes a blunder because I spend 20% of the time doing a mulitpv search calculating scores for root moves,jdart wrote: ↑Sat Feb 02, 2019 3:41 am I think still NN engines even on higher-end commercial graphics cards play blunders at a pretty high rate.
I think there is probably room for a hybrid approach where maybe the NN is suggesting moves to a deep searcher, but I am not aware of anyone pursuing that.
Personally I have a pretty long to-do list for my non-NN engine and I am not planning to drop everything and start building a NN.
--Jon
and then combining that with MCTS scores like: 0.2 * ABscore + 0.8 * MCTSscore. That way the selection of moves at the root is biased
by the alphabeta prior score and that makes it avoid almost all blunders.
-Jonathan