| {"mean_reward": 257.54060924019103, "std_reward": 15.229557544610232, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-22T05:52:38.251212"} |
| {"mean_reward": 257.54060924019103, "std_reward": 15.229557544610232, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-22T05:52:38.251212"} |