| {"mean_reward": -0.5313212290406227, "std_reward": 0.9736758045334537, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-25T14:03:31.977837"} |
| {"mean_reward": -0.5313212290406227, "std_reward": 0.9736758045334537, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-25T14:03:31.977837"} |