| {"mean_reward": -0.21973991664126516, "std_reward": 0.07787211702568067, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-31T05:33:39.497912"} |
| {"mean_reward": -0.21973991664126516, "std_reward": 0.07787211702568067, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-31T05:33:39.497912"} |