| {"mean_reward": -0.21643787827342748, "std_reward": 0.10590321117397547, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-26T06:11:37.495192"} |
| {"mean_reward": -0.21643787827342748, "std_reward": 0.10590321117397547, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-26T06:11:37.495192"} |