| {"mean_reward": 596.0, "std_reward": 196.60620539545542, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-28T11:29:36.560365"} |
| {"mean_reward": 596.0, "std_reward": 196.60620539545542, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-28T11:29:36.560365"} |