Autonomous agent learning by a creativity optimization

Authors:
Chi-Kin Chow;Hung-Tat Tsui
Affiliations:
Visual Signal Processing and Communications Laboratory, Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, New Territory, Hong Kong SAR;Visual Signal Processing and Communications Laboratory, Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, New Territory, Hong Kong SAR
Venue:
Math'04 Proceedings of the 5th WSEAS International Conference on Applied Mathematics
Year:
2004

Citing 9
Cited 0

A foundation for the study of group decision support systems

Management Science
Using a GDSS to facilitate group consensus: some intended and unintended consequences

MIS Quarterly
Effects of anonymity and evaluative tone on idea generation in computer-mediated groups

Management Science
Electronic meeting systems

Communications of the ACM - Special issue on computer graphics: state of the arts
Swarm intelligence

Swarm intelligence
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
Experimental Studies of Group Decision Support Systems: An Assessment of Variables Studied and Methodology

HICSS '97 Proceedings of the 30th Hawaii International Conference on System Sciences: Information Systems Track-Collaboration Systems and Technology - Volume 2
Lessons from a dozen years of group support systems research: a discussion of lab and field findings

Journal of Management Information Systems - Special issue: Information technology and its organizational impact
Stimulating creativity: teaching engineers to be innovators

FIE '98 Proceedings of the 28th Annual Frontiers in Education - Volume 03

Quantified Score

Hi-index	0.00

Visualization

Abstract

In robot applications, the performance of a robot agent is measured by the quantity of award received from its responses to the environment. Many literatures define the response as either a state diagram or a neural network. For some robot applications, the duration and the cost of response evaluating are excessive. Therefore, it is necessary to use as few trials as possible to determine the optimal response. In this paper, a novel global optimization algorithm called "Creativity Optimization" is proposed to tackle this process of response learning. By introducing the concept of creativity, the algorithm can search for the optimum with fewer numbers of trials than those of other popular optimization techniques. Three benchmark functions are provided to illustrate the performance of the proposed algorithm. The results show that it can effectively search the global optima with fewer solution evaluations.