DocumentCode :
3597394
Title :
An Actor-Critic reinforcement learning algorithm based on adaptive RBF network
Author :
Li, Chun-Gui ; Wang, Meng ; Huang, Zhen-Jin ; Zhang, Zeng-Fang
Author_Institution :
Dept. of Comput. Eng., Guangxi Univ. of Technol., Liuzhou, China
Volume :
2
fYear :
2009
Firstpage :
984
Lastpage :
988
Abstract :
We introduce an algorithm of actor-critic reinforcement learning methods in continuous state space. In order to cope with large-scale or continuous state spaces, the algorithm utilizes applied radial basis function (RBF) neural network to approximate the state value function. By training self-adapted non-linear processing unit, realizing online adaptive reconstructing of state space, the approximation is improved. In order to improve the efficient of exploration, a hybrid exploration strategy is proposed. Experimental studies concerning a mountain-car control task illustrate the performance and applicability of the proposed algorithm.
Keywords :
function approximation; learning (artificial intelligence); radial basis function networks; actor-critic reinforcement learning algorithm; adaptive radial basis function neural network; continuous state space; function approximation; hybrid exploration strategy; mountain-car control; selfadapted nonlinear processing unit training; Adaptive systems; Computer networks; Cybernetics; Function approximation; Machine learning; Machine learning algorithms; Neural networks; Radial basis function networks; Space technology; State-space methods; Actor-Critic reinforcement learning; Adaptive RBF network; Exploration strategy; Function approximation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2009 International Conference on
Print_ISBN :
978-1-4244-3702-3
Electronic_ISBN :
978-1-4244-3703-0
Type :
conf
DOI :
10.1109/ICMLC.2009.5212431
Filename :
5212431
Link To Document :
بازگشت