| {"mean_reward": -0.16373540675267578, "std_reward": 0.105025725424128, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-28T15:19:10.499971"} |
| {"mean_reward": -0.16373540675267578, "std_reward": 0.105025725424128, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-28T15:19:10.499971"} |