"A New Reinforcement Learning Algorithm with Fixed Exploration for Semi-Markov Control in Preventive Maintenance" by Angelo Encapera

Article

A New Reinforcement Learning Algorithm with Fixed Exploration for Semi-Markov Control in Preventive Maintenance

Proceedings of the ASME 2017 12th International Manufacturing Science and Engineering Conference (2017, Los Angeles, CA)

Angelo Encapera
Abhijit Gosavi, Missouri University of Science and Technology

Link

Abstract

Artificial intelligence techniques can play a significant role in solving problems encountered in the domain of Total Productive Maintenance (TPM). This paper considers a new reinforcement learning algorithm called iSMART, which can solve semi-Markov decision processes underlying control problems related to TPM. The algorithm uses a constant exploration rate, unlike its precursor R-SMART, which required exploration decay. Numerical experiments conducted here show encouraging behavior with the new algorithm.

Meeting Name

ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 (2017: Jun. 4-8, Los Angeles, CA)

Department(s)

Engineering Management and Systems Engineering

Comments

This research was partially funded by a seed grant from the Department of Engineering Management and Systems Engineering at the Missouri University of Science and Technology.

Keywords and Phrases

Manufacture,
Markov processes,
Preventive maintenance,
Problem solving,
Reinforcement learning,
Artificial intelligence techniques,
Control problems,
Numerical experiments,
Semi-Markov controls,
Semi-Markov decision process,
Total productive maintenance,
Learning algorithms

International Standard Book Number (ISBN)

978-0-7918-5074-9

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

Publication Date

6-1-2017

Publication Date

01 Jun 2017

Disciplines

Operations Research, Systems Engineering and Industrial Engineering

Citation Information

Angelo Encapera and Abhijit Gosavi. "A New Reinforcement Learning Algorithm with Fixed Exploration for Semi-Markov Control in Preventive Maintenance" Proceedings of the ASME 2017 12th International Manufacturing Science and Engineering Conference (2017, Los Angeles, CA) Vol. 3 (2017)
Available at: http://works.bepress.com/abhijit-gosavi/35/