Reinforcement learning control based on multi-goal representation using hierarchical heuristic dynamic programming
Date of Original Version
We are interested in developing a multi-goal generator to provide detailed goal representations that help to improve the performance of the adaptive critic design (ACD). In this paper we propose a hierarchical structure of goal generator networks to cascade external reinforcement into more informative internal goal representations in the ACD. This is in contrast with previous designs in which the external reward signal is assigned to the critic network directly. The ACD control system performance is evaluated on the ball-and-beam balancing benchmark under noise-free and various noisy conditions. Simulation results in the form of a comparative study demonstrate effectiveness of our approach. © 2012 IEEE.
Proceedings of the International Joint Conference on Neural Networks
Ni, Zhen, Haibo He, Dongbin Zhao, and Danil V. Prokhorov. "Reinforcement learning control based on multi-goal representation using hierarchical heuristic dynamic programming." Proceedings of the International Joint Conference on Neural Networks , (2012). doi:10.1109/IJCNN.2012.6252524.