| {"mean_reward": -0.1683712, "std_reward": 0.1005491249775949, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-02T13:39:24.432132"} |
| {"mean_reward": -0.1683712, "std_reward": 0.1005491249775949, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-02T13:39:24.432132"} |