| {"mean_reward": 413.0, "std_reward": 243.20978598732412, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-04T05:16:59.049147"} |
| {"mean_reward": 413.0, "std_reward": 243.20978598732412, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-04T05:16:59.049147"} |