| {"mean_reward": 379.5, "std_reward": 144.14315800619883, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-25T17:21:38.858364"} |
| {"mean_reward": 379.5, "std_reward": 144.14315800619883, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-25T17:21:38.858364"} |