| {"mean_reward": 238.302286, "std_reward": 20.47498926402787, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-05T16:08:05.015104"} |
| {"mean_reward": 238.302286, "std_reward": 20.47498926402787, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-05T16:08:05.015104"} |