Title :
A kind of utility function in adaptive dynamic programming for inverted pendulum control
Author :
Wang, Zhen-Yu ; Dai, Ya-ping ; Li, Yong-wei ; Yao, Yuan
Author_Institution :
Coll. of Autom., Beijing Inst. of Technol., Beijing, China
Abstract :
The inverted pendulum is a complex, classic nonlinear system. In this paper, we apply adaptive dynamic programming that is a learning control method designed by neural network for inverted pendulum control. To achieve a good control performance, a kind of utility function is studied by means of action-dependent heuristic dynamic programming. According to the type of utility function based on power function and exponential function, a novel utility function will be designed in this paper. Using the utility function to design a controller in inverted pendulum system, and comparing with other utility function used in controller for inverted pendulum control problem, improvement experiment result is obtained.
Keywords :
adaptive systems; control system synthesis; dynamic programming; heuristic programming; large-scale systems; learning systems; neurocontrollers; nonlinear control systems; action-dependent heuristic dynamic programming; adaptive dynamic programming; complex system; controller design; exponential function; inverted pendulum control; learning control; neural network; nonlinear system; power function; utility function; Adaptive systems; Dynamic programming; Electric shock; Equations; Machine learning; Mathematical model; Optimal control; Action-dependent heuristic programming; Adaptive dynamic programming; Inverted pendulum control; Neural network; Utility function;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2010 International Conference on
Conference_Location :
Qingdao
Print_ISBN :
978-1-4244-6526-2
DOI :
10.1109/ICMLC.2010.5580816
