| {"mean_reward": 605.0, "std_reward": 255.44079548889601, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-23T15:28:15.613928"} |
| {"mean_reward": 605.0, "std_reward": 255.44079548889601, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-23T15:28:15.613928"} |