{"mean_reward": 682.5, "std_reward": 236.730331812381, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-26T15:59:23.080606"} |
{"mean_reward": 682.5, "std_reward": 236.730331812381, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-26T15:59:23.080606"} |