What are dynamic optimization problems?

Abstract

Dynamic Optimization Problems (DOPs) have been widely studied using Evolutionary Algorithms (EAs). Yet, a clear and rigorous definition of DOPs is lacking in the Evolutionary Dynamic Optimization (EDO) community. In this paper, we propose a unified definition of DOPs based on the idea of multiple-decision-making discussed in the Reinforcement Learning (RL) community. We draw a connection between EDO and RL by arguing that both of them are studying DOPs according to our definition of DOPs. We point out that existing EDO or RL research has been mainly focused on some types of DOPs. A conceptualized benchmark problem, which is aimed at the systematic study of various DOPs, is then developed. Some interesting experimental studies on the benchmark reveal that EDO and RL methods are specialized in certain types of DOPs and more importantly new algorithms for DOPs can be developed by combining the strength of both EDO and RL methods.

Publication DOI: https://doi.org/10.1109/CEC.2014.6900316
Divisions: ?? 50811700Jl ??
Additional Information: © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Event Title: 2014 IEEE Congress on Evolutionary Computation
Event Type: Other
Event Dates: 2014-07-06 - 2014-07-11
Uncontrolled Keywords: Artificial Intelligence,Computational Theory and Mathematics,Theoretical Computer Science
ISBN: 978-1-4799-6626-4
Last Modified: 01 Mar 2024 08:07
Date Deposited: 14 Jan 2015 15:00
Full Text Link: http://ieeexplo ... rnumber=6900316
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Conference contribution
Published Date: 2014
Authors: Fu, Haobo
Lewis, Peter R. (ORCID Profile 0000-0003-4271-8611)
Sendhoff, Bernhard
Tang, Ke
Yao, Xin

Download

[img]

Version: Accepted Version


Export / Share Citation


Statistics

Additional statistics for this record