| {"mean_reward": 660.0, "std_reward": 184.70246343782208, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-14T21:39:37.006055"} |
| {"mean_reward": 660.0, "std_reward": 184.70246343782208, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-14T21:39:37.006055"} |