| {"mean_reward": -0.1991342045366764, "std_reward": 0.12500604136179214, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-27T07:15:01.377246"} |
| {"mean_reward": -0.1991342045366764, "std_reward": 0.12500604136179214, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-27T07:15:01.377246"} |