| {"mean_reward": 262.24422692592015, "std_reward": 13.181752832029751, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-03T04:17:17.473215"} |
| {"mean_reward": 262.24422692592015, "std_reward": 13.181752832029751, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-03T04:17:17.473215"} |