| {"mean_reward": 231.24599851992826, "std_reward": 54.341822235848724, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-05T22:31:46.346473"} |
| {"mean_reward": 231.24599851992826, "std_reward": 54.341822235848724, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-05T22:31:46.346473"} |