| {"mean_reward": 756.0, "std_reward": 79.74333827975852, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-03T18:19:52.064989"} |
| {"mean_reward": 756.0, "std_reward": 79.74333827975852, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-03T18:19:52.064989"} |