| {"mean_reward": -0.23107303236611187, "std_reward": 0.07464856259880695, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-26T14:36:04.648218"} |
| {"mean_reward": -0.23107303236611187, "std_reward": 0.07464856259880695, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-26T14:36:04.648218"} |