Access Restriction

Author Tiong Yew Tang ♦ Egerton, S. ♦ Kubota, N.
Source IEEE Xplore Digital Library
Content type Text
Publisher Institute of Electrical and Electronics Engineers, Inc. (IEEE)
File Format PDF
Copyright Year ©2014
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Special computer methods
Subject Keyword Stress ♦ Biological system modeling ♦ Fuzzy logic ♦ Adaptation models ♦ Mathematical model ♦ Complexity theory
Abstract Biological systems are said to learn from both intrinsic and extrinsic motivations. Extrinsic motivations, largely based on environmental conditions, have been well explored by Reinforcement Learning (RL) methods. Less explored, and more interesting in our opinion, are the possible intrinsic motivations that may drive a learning agent. In this paper we explore such a possibility. We develop a novel intrinsic motivation model which is based on the well known Yerkes and Dodson stress curve theory and the biological principles associated with stress. We use a stress feedback loop to affect the agent's memory capacity for retrieval. The stress and memory signals are fed into a fuzzy logic system which decides upon the best action for the agent to perform against the current best action policy. Our simulated results show that our model significantly improves upon agent learning performance and stability when objectively compared against existing state-of-the-art RL approaches in non-stationary environments and can effectively deal with significantly larger problem domains.
Description Author affiliation: Fac. of Syst. Design, Tokyo Metropolitan Univ., Tokyo, Japan (Kubota, N.) || Sch. of Inf. Technol., Monash Univ. Malaysia, Sunway, Malaysia (Tiong Yew Tang; Egerton, S.)
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research ♦ Reading
Education Level UG and PG
Learning Resource Type Article
Publisher Date 2014-07-06
Publisher Place China
Rights Holder Institute of Electrical and Electronics Engineers, Inc. (IEEE)
e-ISBN 9781479920723
Size (in Bytes) 1.51 MB
Page Count 8
Starting Page 1728
Ending Page 1735

Source: IEEE Xplore Digital Library