| {"mean_reward": -0.17539128232747317, "std_reward": 0.044952774391272786, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-17T12:31:28.757506"} |
| {"mean_reward": -0.17539128232747317, "std_reward": 0.044952774391272786, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-17T12:31:28.757506"} |