| {"mean_reward": -0.18473151475191116, "std_reward": 0.11147082422582022, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-12T13:10:37.153456"} |
| {"mean_reward": -0.18473151475191116, "std_reward": 0.11147082422582022, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-12T13:10:37.153456"} |