| {"mean_reward": 571.5, "std_reward": 238.19162453789176, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-30T11:02:04.282210"} |
| {"mean_reward": 571.5, "std_reward": 238.19162453789176, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-30T11:02:04.282210"} |