| {"mean_reward": 49.5, "std_reward": 30.696090956341656, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-08T15:43:20.036164"} |
| {"mean_reward": 49.5, "std_reward": 30.696090956341656, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-08T15:43:20.036164"} |