| {"mean_reward": 704.5, "std_reward": 200.70438460581772, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-24T14:19:52.561346"} |
| {"mean_reward": 704.5, "std_reward": 200.70438460581772, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-24T14:19:52.561346"} |