The Fuzzy Sars´a´(λ) Learning Approach Applied to a Strategic Route Learning Robot Behaviour

Author

Theodoridis, Theodoros ; Hu, Huosheng

Author_Institution

Dept. of Comput. Sci., Essex Univ., Colchester

fYear

2006

fDate

9-15 Oct. 2006

Firstpage

1767

Lastpage

1772

Abstract

This paper presents a novel Fuzzy Sarsa(λ) Learning (FSλL) approach applied to a strategic route leaning task of a mobile robot. FSlambdaL is a hybrid architecture that combines reinforcement learning and fuzzy logic control. The Sarsa(λ) learning algorithm is used to tune the rule-base of a fuzzy Logic controller which has been tested in a route learning task. The robot explores its environment using its fixed experience provided by a discretized fuzzy logic controller, and then learns optimal policies to achieve goals in less time and less error.

Keywords

control system synthesis; fuzzy control; knowledge based systems; learning (artificial intelligence); mobile robots; Fuzzy Sarsa(λ) Learning; controller tuning; discretized controller; fuzzy logic control; hybrid architecture; mobile robots; reinforcement learning; rule-base control; strategic route learning robot behaviour; Acceleration; Automatic control; Engines; Error correction; Fuzzy control; Fuzzy logic; Intelligent robots; Learning; Robot control; Robot kinematics; Fuzzy Logic Controllers; Fuzzy Q-Learning; Reinforcement Learning; Robot Autonomy; Sarsa(λ);

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Robots and Systems, 2006 IEEE/RSJ International Conference on

Conference_Location

Beijing

Print_ISBN

1-4244-0258-1

Electronic_ISBN

1-4244-0259-X

Type

conf

DOI

10.1109/IROS.2006.282215

Filename

4058632