{"mean_reward": 604.5, "std_reward": 182.2422837872704, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-07-08T20:23:27.646920"} |
{"mean_reward": 604.5, "std_reward": 182.2422837872704, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-07-08T20:23:27.646920"} |