| {"mean_reward": -0.2155437221750617, "std_reward": 0.09078659262988904, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-31T18:21:59.372825"} |
| {"mean_reward": -0.2155437221750617, "std_reward": 0.09078659262988904, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-31T18:21:59.372825"} |