| {"mean_reward": 543.0, "std_reward": 166.67633305301626, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-12T11:48:20.225298"} |
| {"mean_reward": 543.0, "std_reward": 166.67633305301626, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-12T11:48:20.225298"} |