Zeta36 / chess-alpha-zero

Chess reinforcement learning by AlphaGo Zero methods.
MIT License
2.13k stars 481 forks source link

After fresh SL training data not able to start training. #91

Open Unimax opened 4 years ago

Unimax commented 4 years ago

so i generate sl data from png files then i tried to run opt mode but even if i use --new arg it say "Best model can not loaded!"

i guess optimize.py also need if self.config.opts.new then create and save new base model condition from self-play.py

I understand its not an active project.