| {"mean_reward": -0.2840399418026209, "std_reward": 0.09797117918627914, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-26T08:34:32.451595"} |
| {"mean_reward": -0.2840399418026209, "std_reward": 0.09797117918627914, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-26T08:34:32.451595"} |