| {"mean_reward": 269.2933938344507, "std_reward": 12.614866096422656, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-09T13:54:22.868501"} |
| {"mean_reward": 269.2933938344507, "std_reward": 12.614866096422656, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-09T13:54:22.868501"} |