rl_huggingface / results.json
noobiebuilder's picture
RL course implementation
9ec8ce7 verified
raw
history blame
157 Bytes
{"mean_reward": 239.5836658, "std_reward": 20.71865205320441, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-16T04:42:01.950766"}