{"mean_reward": -0.1433590820990503, "std_reward": 0.08940681705155903, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-31T20:48:41.046865"} |
{"mean_reward": -0.1433590820990503, "std_reward": 0.08940681705155903, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-31T20:48:41.046865"} |