| {"mean_reward": -0.1741826952667907, "std_reward": 0.09594527006430881, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-11T00:46:06.544856"} |
| {"mean_reward": -0.1741826952667907, "std_reward": 0.09594527006430881, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-11T00:46:06.544856"} |