Sample-based potentials estimation for the optimal control of stochastic system
- Resource Type
- Conference
- Authors
- Cheng, Kang; Zhang, Kanjian; Fei, Shumin; Liu, Xiao-Mei
- Source
- Proceedings of the 30th Chinese Control Conference Control Conference (CCC), 2011 30th Chinese. :2031-2035 Jul, 2011
- Subject
- Robotics and Control Systems
Power, Energy and Industry Applications
Components, Circuits, Devices and Systems
Communication, Networking and Broadcast Technologies
Computing and Processing
Markov processes
Least squares approximation
Mathematical model
Equations
Aerospace electronics
Stochastic systems
Stochastic System
Potentials
Markov Decision Processes
Policy Iteration
Basis Function
- Language
- ISSN
- 1934-1768
2161-2927
An optimization method based on perturbation analysis is applied to stochastic system. A policy iteration approach is designed by the performance sensitivity formula which is constructed with potentials. For estimating the potentials, the Poisson equation is viewed as a system of linear equation, then a least squares policy evaluation method is adopted, and the selection of basis function is also discussed for getting a better performance of approximation. The simulation shows the effectiveness of the policy iteration and the approximation approach.