Learning Control of Inverted Pendulum Using Neural Networks.

신경회로망을 이용한 도립진자의 학습제어

A priori information of object is needed to control in some well known control methods. But we can't always know a priori information of object in real world. In this paper, the inverted pendulum is simulated as a control task with the goal of learning to balance the pendulum with no a priori information using neural network controller. In contrast to other applications of neural networks to the inverted pendulum task, the performance feedback is unavailable on each training step, appearing only as a failure signal when the pendulum falls or reaches the bound of track. To solve this task, the delayed performance evaluation and the learning of nonlinear of nonlinear functions must be dealt. Reinforcement learning method is used for those issues.