| {"mean_reward": -40.0, "std_reward": 20.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-18T20:08:35.666739"} |
| {"mean_reward": -40.0, "std_reward": 20.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-18T20:08:35.666739"} |