| {"mean_reward": -0.21662716884166003, "std_reward": 0.0969338466685772, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-02T19:57:23.376196"} |
| {"mean_reward": -0.21662716884166003, "std_reward": 0.0969338466685772, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-02T19:57:23.376196"} |