Chess reinforcement learning by AlphaGo Zero methods

bhamadicharef · Post by **bhamadicharef** » Sun Mar 04, 2018 11:38 am

Hi all

Chess reinforcement learning by AlphaGo Zero methods
https://github.com/Zeta36/chess-alpha-zero

Enjoy !

CheckersGuy · Post by **CheckersGuy** » Sun Mar 04, 2018 12:03 pm

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)

brianr · Post by **brianr** » Sun Mar 04, 2018 2:18 pm

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

Henk · Post by **Henk** » Fri Mar 09, 2018 9:57 am

Maybe better forget it. It's too slow for normal hardware.

brianr · Post by **brianr** » Fri Mar 09, 2018 1:16 pm

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.

Henk · Post by **Henk** » Fri Mar 09, 2018 1:31 pm

4673 output nodes and (8? *) 19 * 64 input nodes makes each network slow.

brianr · Post by **brianr** » Fri Mar 09, 2018 3:11 pm

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) :

Chess reinforcement learning by AlphaGo Zero methods

Chess reinforcement learning by AlphaGo Zero methods

Re: Chess reinforcement learning by AlphaGo Zero methods

Re: Chess reinforcement learning by AlphaGo Zero methods

Re: Chess reinforcement learning by AlphaGo Zero methods

Re: Chess reinforcement learning by AlphaGo Zero methods

Re: Chess reinforcement learning by AlphaGo Zero methods

Re: Chess reinforcement learning by AlphaGo Zero methods