search

SforAiDl / genrl

A PyTorch reinforcement learning library for generalizable and reproducible algorithm implementations with an aim to improve accessibility in RL
https://genrl.readthedocs.io
MIT License
402 stars 59 forks source link

fix evaluate function in ClassicalTrainer #395

Open lunmre opened 3 years ago

lunmre commented 3 years ago
  1. add reset of env and 'ep_rew' after each evaluation episode ends
  2. fix parameter passing of 'eval_ep' in evaluate func