| {"mean_reward": 256.37361149641447, "std_reward": 15.939202958800475, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-27T12:09:23.924571"} |
| {"mean_reward": 256.37361149641447, "std_reward": 15.939202958800475, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-27T12:09:23.924571"} |