| {"mean_reward": 276.35615125677384, "std_reward": 12.559491055736679, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-24T16:39:36.008642"} |
| {"mean_reward": 276.35615125677384, "std_reward": 12.559491055736679, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-24T16:39:36.008642"} |