| {"mean_reward": -0.23317240811884404, "std_reward": 0.1299734184209891, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-16T20:41:27.824041"} |
| {"mean_reward": -0.23317240811884404, "std_reward": 0.1299734184209891, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-16T20:41:27.824041"} |