{ "env_name": "Acrobot-v1", "estimator_name": "ensemble.RandomForestClassifier", "seed": 44, "max_episode": 500, "collect_iter": 15, "train_per_iter": 1, "batch_size": 0, "warm_up": 50, "memory_size": 700, "last_few": 75, "testing_period": 10, "horizon_scale": 0.02, "return_scale": 0.02, "epsilon": 0.2, "final_desired_return": -79, "final_desired_horizon": 82 }