Chess-Zero
Chess-Zero copied to clipboard
Akababa
Chess reinforcement learning by AlphaZero methods.
Results
2
Chess-Zero issues
Sort by
recently updated
recently updated
newest added
https://github.com/Akababa/Chess-Zero/blob/90a5aad05656131506239388557b9f60d16235a3/src/chess_zero/worker/self_play.py#L33-L41 I see you create max_processes pipe list of search_threads pipes and max_processes execute self play processes with the pipe list. A self player use own pipe list by pop...
@benediamond @Zeta36 After many hours of hopeless debugging I discovered locks which are amazing. The overall speedup on my machine is quite a lot, I would say at least 2x....
