| {"mean_reward": 267.2396031, "std_reward": 33.05586668856894, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-01T13:11:12.659271"} |
| {"mean_reward": 267.2396031, "std_reward": 33.05586668856894, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-01T13:11:12.659271"} |