| {"mean_reward": 541.0, "std_reward": 181.10494195355355, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-06T18:46:30.303306"} |
| {"mean_reward": 541.0, "std_reward": 181.10494195355355, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-06T18:46:30.303306"} |