| {"mean_reward": -0.22199183432385325, "std_reward": 0.09826259855446925, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-05T12:13:21.339586"} |
| {"mean_reward": -0.22199183432385325, "std_reward": 0.09826259855446925, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-05T12:13:21.339586"} |