| {"mean_reward": 570.0, "std_reward": 248.19347291981714, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-16T06:54:11.569296"} |
| {"mean_reward": 570.0, "std_reward": 248.19347291981714, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-16T06:54:11.569296"} |