| {"mean_reward": 318.5, "std_reward": 118.68129591473124, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-05T11:05:33.176694"} |
| {"mean_reward": 318.5, "std_reward": 118.68129591473124, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-05T11:05:33.176694"} |