search

Zeta36 / chess-alpha-zero

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

Will you take more time in every iteration with training process? #79

Open yeates opened 5 years ago

yeates commented 5 years ago
  1. From the beginning, I finish one iteration need 300s, however, it needs 3000s when finished almost 20 times iteration. Is that OK?
  2. And, RAM up with training process too! how can I solve this?