DocumentCode :
2894789
Title :
Active Exploration Planning in Reinforcement Learning for Inverted Pendulum System Control
Author :
Zheng, Yu ; Luo, Si-Wei ; Zi-Ang Lv
Author_Institution :
Sch. of Comput. & Inf. Technol., Jiaotong Univ., Beijing
fYear :
2006
fDate :
13-16 Aug. 2006
Firstpage :
2805
Lastpage :
2809
Abstract :
Reinforcement learning method usually require that all actions be tried in all state infinitely often for convergence. Such algorithms are impractical to be applied to sophisticated systems due to its low learning efficiency. This paper analyses the problem of limit cycles exist in reinforcement learning for inverted pendulum system control and proposed active exploration planning policy. The algorithm sufficiently makes use of characteristics, active detects limit cycles and plan exploration instead by random exploration. The algorithm action improved the learning efficiency by selecting sub-optimal control action and limiting the exploration to the controllable areas, which can make the number of trials not grow exponentially with the state space. Simulation results for the control of single and double inverted pendulum are presented to show effectiveness of the proposed algorithm
Keywords :
learning (artificial intelligence); nonlinear systems; pendulums; suboptimal control; active exploration planning; inverted pendulum system control; random exploration; reinforcement learning method; suboptimal control action; Acceleration; Control systems; Convergence; Cybernetics; Information technology; Intelligent control; Learning systems; Limit-cycles; Machine learning; Machine learning algorithms; Optimal control; State-space methods; Technology planning; Reinforcement learning; exploration policy; inverted pendulum;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2006 International Conference on
Conference_Location :
Dalian, China
Print_ISBN :
1-4244-0061-9
Type :
conf
DOI :
10.1109/ICMLC.2006.259002
Filename :
4028538
Link To Document :
بازگشت