| {"mean_reward": 274.08307458665934, "std_reward": 15.091362088044072, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-10T20:01:34.169779"} |
| {"mean_reward": 274.08307458665934, "std_reward": 15.091362088044072, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-10T20:01:34.169779"} |