| {"mean_reward": 630.0, "std_reward": 148.8959368149447, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-06T11:21:09.464180"} |
| {"mean_reward": 630.0, "std_reward": 148.8959368149447, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-06T11:21:09.464180"} |