| {"mean_reward": 585.0, "std_reward": 157.35310610216754, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-31T07:49:45.180358"} |
| {"mean_reward": 585.0, "std_reward": 157.35310610216754, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-31T07:49:45.180358"} |