Hi all
Chess reinforcement learning by AlphaGo Zero methods
https://github.com/Zeta36/chess-alpha-zero
Enjoy !
Chess reinforcement learning by AlphaGo Zero methods
Moderators: hgm, Rebel, chrisw
-
- Posts: 31
- Joined: Fri Nov 25, 2016 10:14 am
- Location: Singapore
Chess reinforcement learning by AlphaGo Zero methods
Brahim HAMADICHAREF
Singapore
Singapore
-
- Posts: 273
- Joined: Wed Aug 24, 2016 9:49 pm
Re: Chess reinforcement learning by AlphaGo Zero methods
This github repo was already posted ( if not in multiple times). Still, I would really like chess-alpha-zero to be as popular as the go variant (LeelaZero)
-
- Posts: 536
- Joined: Thu Mar 09, 2006 3:01 pm
Re: Chess reinforcement learning by AlphaGo Zero methods
That repo is largely dormant, although I am still fiddling with it (not as the owner).
Most are looking here, which is becoming ready for widespread use:
https://github.com/glinscott/leela-chess
Most are looking here, which is becoming ready for widespread use:
https://github.com/glinscott/leela-chess
-
- Posts: 7218
- Joined: Mon May 27, 2013 10:31 am
Re: Chess reinforcement learning by AlphaGo Zero methods
Maybe better forget it. It's too slow for normal hardware.
-
- Posts: 536
- Joined: Thu Mar 09, 2006 3:01 pm
Re: Chess reinforcement learning by AlphaGo Zero methods
Depends on your point of view. I've been doing computer chess since 1971, but not very well. Tinker is consistently in the top of the bottom third of engines. Hah. For me, it is about the journey.
Trying to understand the AZ approach and watching my gpu chew on the NN until things train a bit more is satisfying enough. The Leela Chess team is far ahead, like Fishtest with Stockfish, but holds real promise with a more crafted NN and tuning approach fueled by crowd-sourced horsepower.
Trying to understand the AZ approach and watching my gpu chew on the NN until things train a bit more is satisfying enough. The Leela Chess team is far ahead, like Fishtest with Stockfish, but holds real promise with a more crafted NN and tuning approach fueled by crowd-sourced horsepower.
-
- Posts: 7218
- Joined: Mon May 27, 2013 10:31 am
Re: Chess reinforcement learning by AlphaGo Zero methods
4673 output nodes and (8? *) 19 * 64 input nodes makes each network slow.
-
- Posts: 536
- Joined: Thu Mar 09, 2006 3:01 pm
Re: Chess reinforcement learning by AlphaGo Zero methods
Yup, which is why I started looking at tic-tac-toe.
That NN is very fast with the AZ approach.
Then, I looked at Othello.
Thanks to https://github.com/suragnair/alpha-zero-general
Its NN is considerably slower, but the game is far more complex.
Of course, it is another major complexity jump to chess.
Mangling: Don't bring a knife NN brain to a gunfight (chess or go) :
That NN is very fast with the AZ approach.
Then, I looked at Othello.
Thanks to https://github.com/suragnair/alpha-zero-general
Its NN is considerably slower, but the game is far more complex.
Of course, it is another major complexity jump to chess.
Mangling: Don't bring a knife NN brain to a gunfight (chess or go) :