| {"mean_reward": 454.0, "std_reward": 84.72897969408106, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-01-08T20:12:09.444652"} |
| {"mean_reward": 454.0, "std_reward": 84.72897969408106, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-01-08T20:12:09.444652"} |