| {"mean_reward": 638.0, "std_reward": 227.1585349486125, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-11T22:23:11.037210"} |
| {"mean_reward": 638.0, "std_reward": 227.1585349486125, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-11T22:23:11.037210"} |