| {"mean_reward": 241.099177732717, "std_reward": 46.819208909586315, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-21T09:12:20.039522"} |
| {"mean_reward": 241.099177732717, "std_reward": 46.819208909586315, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-21T09:12:20.039522"} |