| {"mean_reward": -0.21777675151824952, "std_reward": 0.088106062599681, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-07T15:22:05.365759"} |
| {"mean_reward": -0.21777675151824952, "std_reward": 0.088106062599681, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-07T15:22:05.365759"} |