| {"mean_reward": -0.2057877941057086, "std_reward": 0.0745303825305576, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-01T00:03:40.077266"} |
| {"mean_reward": -0.2057877941057086, "std_reward": 0.0745303825305576, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-01T00:03:40.077266"} |