| {"mean_reward": 584.5, "std_reward": 120.96383757139982, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-04-06T14:07:28.001508"} |
| {"mean_reward": 584.5, "std_reward": 120.96383757139982, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-04-06T14:07:28.001508"} |