| {"mean_reward": -0.8636558000000001, "std_reward": 1.8547579192024388, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-26T21:40:52.118808"} |
| {"mean_reward": -0.8636558000000001, "std_reward": 1.8547579192024388, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-26T21:40:52.118808"} |