Postural control of two-stage inverted pendulum using reinforcement learning and self-organizing map

초록

This paper considers reinforcement learning control with the self-organizing map. Reinforcement learning uses the observable states of objective system and signals from interaction of the system and environment as input data. For fast learning in neural network training, it is necessary to reduce learning data. In this paper, we use the self-organizing map to partition the observable states. Partitioning states reduces the number of learning data which is used for training neural networks. And neural dynamic programming design method is used for the controller. For evaluating the designed reinforcement learning controller, a double linked inverted pendulum on the cart system is simulated. The designed controller is composed of serial connection of self-organizing map and two Multi-layer Feed-Forward Neural Networks.