| {"mean_reward": 600.0, "std_reward": 117.13240371477058, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-22T23:15:00.501709"} |
| {"mean_reward": 600.0, "std_reward": 117.13240371477058, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-22T23:15:00.501709"} |