| {"mean_reward": 256.0, "std_reward": 27.184554438136374, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-29T20:35:58.350027"} |
| {"mean_reward": 256.0, "std_reward": 27.184554438136374, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-29T20:35:58.350027"} |