Data-driven learning and control with multiple critic networks
Date of Original Version
In this paper, we extend our previous work of a three-network adaptive dynamic programming design  to be a multiple critic networks design for online learning and control. The key idea of this approach is to develop a hierarchical internal goal representation to facilitate the online learning with detailed and informative internal value signal representations. We present our learning architecture in detail, and also demonstrate its performance on the popular cartpole balancing benchmark. Simulation results demonstrate the effectiveness of our approach. We also present discussions of further research directions along this topic. © 2012 IEEE.
Publication Title, e.g., Journal
Proceedings of the World Congress on Intelligent Control and Automation (WCICA)
He, Haibo, Zhen Ni, and Dongbin Zhao. "Data-driven learning and control with multiple critic networks." Proceedings of the World Congress on Intelligent Control and Automation (WCICA) (2012): 523-527. doi: 10.1109/WCICA.2012.6357935.