Page 1 of 1
Chess reinforcement learning by AlphaGo Zero methods
Posted: Sun Mar 04, 2018 11:38 am
by bhamadicharef
Hi all
Chess reinforcement learning by AlphaGo Zero methods
https://github.com/Zeta36/chess-alpha-zero
Enjoy !
Re: Chess reinforcement learning by AlphaGo Zero methods
Posted: Sun Mar 04, 2018 12:03 pm
by CheckersGuy
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)
Re: Chess reinforcement learning by AlphaGo Zero methods
Posted: Sun Mar 04, 2018 2:18 pm
by brianr
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
Re: Chess reinforcement learning by AlphaGo Zero methods
Posted: Fri Mar 09, 2018 9:57 am
by Henk
Maybe better forget it. It's too slow for normal hardware.
Re: Chess reinforcement learning by AlphaGo Zero methods
Posted: Fri Mar 09, 2018 1:16 pm
by brianr
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.
Re: Chess reinforcement learning by AlphaGo Zero methods
Posted: Fri Mar 09, 2018 1:31 pm
by Henk
4673 output nodes and (8? *) 19 * 64 input nodes makes each network slow.
Re: Chess reinforcement learning by AlphaGo Zero methods
Posted: Fri Mar 09, 2018 3:11 pm
by brianr
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) :