| {"mean_reward": -48.683, "std_reward": 7.906105931493708, "is_deterministic": true, "n_eval_episodes": 1000, "eval_datetime": "2025-10-18T07:28:59.372692"} |
| {"mean_reward": -48.683, "std_reward": 7.906105931493708, "is_deterministic": true, "n_eval_episodes": 1000, "eval_datetime": "2025-10-18T07:28:59.372692"} |