Reinforcement learning in continuous state space with perceptual aliasing by using complex-valued RBF network

Author

Shibuya, Takeshi ; Arita, Hideaki ; Hamagami, Tomoki

Author_Institution

Grad. Sch. of Syst. & Inf. Eng., Univ. of Tsukuba, Tsukuba, Japan

fYear

2010

fDate

10-13 Oct. 2010

Firstpage

1799

Lastpage

1803

Abstract

Reinforcement learning for continuous state space with perceptual aliasing is proposed. Complex-valued reinforcement learning is effective for perceptual aliasing. In continuous state space, the conventional complex-valued reinforcement learning demands the discretization of continuous state. However, it is difficult to discretize continuous state suitably. In this paper, complex-valued reinforcement learning using complex-valued RBF network is proposed. An experiment shows that proposed method is effective for continuous state space with perceptual aliasing.

Keywords

Markov processes; antialiasing; learning (artificial intelligence); radial basis function networks; Markov process; complex valued RBF Network; continuous state space; perceptual aliasing; reinforcement learning; Radial basis function networks; complex-valued reinforcement learning; partially observable Markov decision Processes; perceptual Aliasing; reinforcement learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems Man and Cybernetics (SMC), 2010 IEEE International Conference on

Conference_Location

Istanbul

ISSN

1062-922X

Print_ISBN

978-1-4244-6586-6

Type

conf

DOI

10.1109/ICSMC.2010.5642294

Filename

5642294