| {"mean_reward": -0.28693558275699615, "std_reward": 0.073586249834246, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-12T06:26:52.909554"} |
| {"mean_reward": -0.28693558275699615, "std_reward": 0.073586249834246, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-12T06:26:52.909554"} |