{"mean_reward": -0.29179658479988574, "std_reward": 0.11305152806237288, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-13T22:42:50.628014"} |
{"mean_reward": -0.29179658479988574, "std_reward": 0.11305152806237288, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-13T22:42:50.628014"} |