| {"mean_reward": -0.21317853378131985, "std_reward": 0.10243084228756567, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-18T06:17:01.907615"} |
| {"mean_reward": -0.21317853378131985, "std_reward": 0.10243084228756567, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-18T06:17:01.907615"} |