ppo-LunarLander-v2 / results.json
rahulsnkr's picture
deep rl hf course unit1 ppo lunarlander
b900894
{"mean_reward": 263.24364970335034, "std_reward": 16.093639346802632, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-13T15:39:37.511457"}