Offline and online time in Sequential Decision-Making Problems

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A connection has recently been drawn between Dynamic Optimization Problems (DOPs) and Reinforcement Learning Problems (RLPs) where they can be seen as subsets of a broader class of Sequential Decision-Making Problems (SDMPs). SDMPs require new decisions on an ongoing basis. Typically the underlying environment changes between decisions. The SDMP view is useful as it allows the unified space to be explored. Solutions can be designed for characteristics of problem instances using algorithms from either community. Little has been done on comparing algorithm performance across these communities, particularly under real-world resource constraints.

LanguageEnglish
Title of host publication2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
PublisherIEEE
Number of pages8
ISBN (Electronic)978-1-5090-4240-1
DOIs
Publication statusPublished - 9 Feb 2017
Event2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016 - Athens, Greece
Duration: 6 Dec 20169 Dec 2016

Conference

Conference2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
CountryGreece
CityAthens
Period6/12/169/12/16

Fingerprint

Decision making
Decision Making
Reinforcement learning
Dynamic Optimization Problems
Resource Constraints
Reinforcement Learning
Sequential decision making
Subset
Community
Optimization problem
Dynamic optimization
Resource constraints

Bibliographical note

-

Cite this

Soni, A., Lewis, P. R., & Ekárt, A. (2017). Offline and online time in Sequential Decision-Making Problems. In 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016 [7849961] IEEE. https://doi.org/10.1109/SSCI.2016.7849961
Soni, Aman ; Lewis, Peter R. ; Ekárt, Anikó. / Offline and online time in Sequential Decision-Making Problems. 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016. IEEE, 2017.
@inproceedings{e962b22326874e1a9e3033efa8d7441e,
title = "Offline and online time in Sequential Decision-Making Problems",
abstract = "A connection has recently been drawn between Dynamic Optimization Problems (DOPs) and Reinforcement Learning Problems (RLPs) where they can be seen as subsets of a broader class of Sequential Decision-Making Problems (SDMPs). SDMPs require new decisions on an ongoing basis. Typically the underlying environment changes between decisions. The SDMP view is useful as it allows the unified space to be explored. Solutions can be designed for characteristics of problem instances using algorithms from either community. Little has been done on comparing algorithm performance across these communities, particularly under real-world resource constraints.",
author = "Aman Soni and Lewis, {Peter R.} and Anik{\'o} Ek{\'a}rt",
note = "-",
year = "2017",
month = "2",
day = "9",
doi = "10.1109/SSCI.2016.7849961",
language = "English",
booktitle = "2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016",
publisher = "IEEE",
address = "United States",

}

Soni, A, Lewis, PR & Ekárt, A 2017, Offline and online time in Sequential Decision-Making Problems. in 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016., 7849961, IEEE, 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016, Athens, Greece, 6/12/16. https://doi.org/10.1109/SSCI.2016.7849961

Offline and online time in Sequential Decision-Making Problems. / Soni, Aman; Lewis, Peter R.; Ekárt, Anikó.

2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016. IEEE, 2017. 7849961.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Offline and online time in Sequential Decision-Making Problems

AU - Soni, Aman

AU - Lewis, Peter R.

AU - Ekárt, Anikó

N1 - -

PY - 2017/2/9

Y1 - 2017/2/9

N2 - A connection has recently been drawn between Dynamic Optimization Problems (DOPs) and Reinforcement Learning Problems (RLPs) where they can be seen as subsets of a broader class of Sequential Decision-Making Problems (SDMPs). SDMPs require new decisions on an ongoing basis. Typically the underlying environment changes between decisions. The SDMP view is useful as it allows the unified space to be explored. Solutions can be designed for characteristics of problem instances using algorithms from either community. Little has been done on comparing algorithm performance across these communities, particularly under real-world resource constraints.

AB - A connection has recently been drawn between Dynamic Optimization Problems (DOPs) and Reinforcement Learning Problems (RLPs) where they can be seen as subsets of a broader class of Sequential Decision-Making Problems (SDMPs). SDMPs require new decisions on an ongoing basis. Typically the underlying environment changes between decisions. The SDMP view is useful as it allows the unified space to be explored. Solutions can be designed for characteristics of problem instances using algorithms from either community. Little has been done on comparing algorithm performance across these communities, particularly under real-world resource constraints.

UR - http://ieeexplore.ieee.org/document/7849961/

UR - http://www.scopus.com/inward/record.url?scp=85016042103&partnerID=8YFLogxK

U2 - 10.1109/SSCI.2016.7849961

DO - 10.1109/SSCI.2016.7849961

M3 - Conference contribution

BT - 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016

PB - IEEE

ER -

Soni A, Lewis PR, Ekárt A. Offline and online time in Sequential Decision-Making Problems. In 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016. IEEE. 2017. 7849961 https://doi.org/10.1109/SSCI.2016.7849961