ppo-LunarLander-v2 / results.json
Kenemo's picture
more training steps
f42d704
raw
history blame contribute delete
165 Bytes
{"mean_reward": 272.85160621641995, "std_reward": 22.165787185935997, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-24T20:23:56.581753"}