ppo-LunarLander / results.json
arminmrm93's picture
publish trained PPO
6013e2d
raw
history blame contribute delete
165 Bytes
{"mean_reward": 254.29472090000004, "std_reward": 24.190799398130707, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-14T18:58:30.027297"}