| {"mean_reward": 762.0, "std_reward": 214.11679056066575, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-01T02:21:53.721061"} |
| {"mean_reward": 762.0, "std_reward": 214.11679056066575, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-01T02:21:53.721061"} |