| {"mean_reward": -172.064422330854, "std_reward": 31.5619682172839, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-01T02:45:13.506365"} |
| {"mean_reward": -172.064422330854, "std_reward": 31.5619682172839, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-01T02:45:13.506365"} |