| {"mean_reward": 265.60313298188134, "std_reward": 19.935914242256363, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-31T01:29:55.908343"} |
| {"mean_reward": 265.60313298188134, "std_reward": 19.935914242256363, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-31T01:29:55.908343"} |