Evolutionary Algorithms, Markov Decision Processes, Adaptive Critic Designs, and Clustering: Commonalities, Hybridization and Performance

Donald C. Wunsch; Samuel A. Mulder

doi:10.1109/ICISIP.2004.1287704

Evolutionary Algorithms, Markov Decision Processes, Adaptive Critic Designs, and Clustering: Commonalities, Hybridization and Performance

Donald C. Wunsch
, Samuel A. Mulder

Research output: Contribution to journal › Article › peer-review

Abstract

We briefly review and compare the mathematical formulation of Markov decision processes (MDP) and evolutionary algorithms (EA). In so doing, we observe that the adaptive critic design (ACD) approach to MDP can be viewed as a special form of EA. This leads us to pose pertinent questions about possible expansions of the methodology of ACD. This expansive view of EA is not limited to ACD. We discuss how it is possible to consider the powerful chained Lin Kernighan (chained LK) algorithm for the traveling salesman problem (TSP) as a degenerate case of EA. Finally, we review some recent TSP results, using clustering to divide-and-conquer, that provide superior speed and scalability.

Original language	American English
Journal	Proceedings of the International Conference on Intelligent Sensing and Information Processing, 2004
DOIs	https://doi.org/10.1109/ICISIP.2004.1287704
State	Published - Jan 1 2004

Keywords

Adaptive Critic Design
Chained Lin Kernighan Algorithm
Divide and Conquer Methods
Evolutionary Algorithms
Evolutionary Computation
Markov Decision Process
Markov Processes
Traveling Salesman Problem
Travelling Salesman Problems

Disciplines

Electrical and Computer Engineering

Access to Document

10.1109/ICISIP.2004.1287704License: Unspecified

Evolutionary Algorithms Markov Decision Processes Adaptive CritFinal published version, 590 KBLicense: Unspecified

Cite this

@article{90fc264e0b2f4c7ab07d52511256495a,

title = "Evolutionary Algorithms, Markov Decision Processes, Adaptive Critic Designs, and Clustering: Commonalities, Hybridization and Performance",

abstract = " We briefly review and compare the mathematical formulation of Markov decision processes (MDP) and evolutionary algorithms (EA). In so doing, we observe that the adaptive critic design (ACD) approach to MDP can be viewed as a special form of EA. This leads us to pose pertinent questions about possible expansions of the methodology of ACD. This expansive view of EA is not limited to ACD. We discuss how it is possible to consider the powerful chained Lin Kernighan (chained LK) algorithm for the traveling salesman problem (TSP) as a degenerate case of EA. Finally, we review some recent TSP results, using clustering to divide-and-conquer, that provide superior speed and scalability.",

keywords = "Adaptive Critic Design, Chained Lin Kernighan Algorithm, Divide and Conquer Methods, Evolutionary Algorithms, Evolutionary Computation, Markov Decision Process, Markov Processes, Traveling Salesman Problem, Travelling Salesman Problems",

author = "Wunsch, \{Donald C.\} and Mulder, \{Samuel A.\}",

year = "2004",

month = jan,

day = "1",

doi = "10.1109/ICISIP.2004.1287704",

language = "American English",

journal = "Proceedings of the International Conference on Intelligent Sensing and Information Processing, 2004",

}

TY - JOUR

T1 - Evolutionary Algorithms, Markov Decision Processes, Adaptive Critic Designs, and Clustering: Commonalities, Hybridization and Performance

AU - Wunsch, Donald C.

AU - Mulder, Samuel A.

PY - 2004/1/1

Y1 - 2004/1/1

N2 - We briefly review and compare the mathematical formulation of Markov decision processes (MDP) and evolutionary algorithms (EA). In so doing, we observe that the adaptive critic design (ACD) approach to MDP can be viewed as a special form of EA. This leads us to pose pertinent questions about possible expansions of the methodology of ACD. This expansive view of EA is not limited to ACD. We discuss how it is possible to consider the powerful chained Lin Kernighan (chained LK) algorithm for the traveling salesman problem (TSP) as a degenerate case of EA. Finally, we review some recent TSP results, using clustering to divide-and-conquer, that provide superior speed and scalability.

AB - We briefly review and compare the mathematical formulation of Markov decision processes (MDP) and evolutionary algorithms (EA). In so doing, we observe that the adaptive critic design (ACD) approach to MDP can be viewed as a special form of EA. This leads us to pose pertinent questions about possible expansions of the methodology of ACD. This expansive view of EA is not limited to ACD. We discuss how it is possible to consider the powerful chained Lin Kernighan (chained LK) algorithm for the traveling salesman problem (TSP) as a degenerate case of EA. Finally, we review some recent TSP results, using clustering to divide-and-conquer, that provide superior speed and scalability.

KW - Adaptive Critic Design

KW - Chained Lin Kernighan Algorithm

KW - Divide and Conquer Methods

KW - Evolutionary Algorithms

KW - Evolutionary Computation

KW - Markov Decision Process

KW - Markov Processes

KW - Traveling Salesman Problem

KW - Travelling Salesman Problems

UR - https://scholarsmine.mst.edu/ele_comeng_facwork/1607

U2 - 10.1109/ICISIP.2004.1287704

DO - 10.1109/ICISIP.2004.1287704

M3 - Article

JO - Proceedings of the International Conference on Intelligent Sensing and Information Processing, 2004

JF - Proceedings of the International Conference on Intelligent Sensing and Information Processing, 2004

ER -

Evolutionary Algorithms, Markov Decision Processes, Adaptive Critic Designs, and Clustering: Commonalities, Hybridization and Performance

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this