| {"mean_reward": -0.22746915854513644, "std_reward": 0.13471231897738103, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-22T16:35:14.035912"} |
| {"mean_reward": -0.22746915854513644, "std_reward": 0.13471231897738103, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-22T16:35:14.035912"} |