Offline and online time in Sequential Decision-Making Problems

Aman Soni; Peter R. Lewis; Anikó Ekárt

doi:10.1109/SSCI.2016.7849961

Offline and online time in Sequential Decision-Making Problems

Aman Soni, Peter R. Lewis, Anikó Ekárt

Computer Science Research Group

Research output: Chapter in Book/Published conference output › Conference publication

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.

Original language	English
Title of host publication	2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
Publisher	IEEE
Number of pages	8
ISBN (Electronic)	978-1-5090-4240-1
DOIs	https://doi.org/10.1109/SSCI.2016.7849961
Publication status	Published - 9 Feb 2017
Event	2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016 - Athens, Greece Duration: 6 Dec 2016 → 9 Dec 2016

Conference

Conference	2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
Country/Territory	Greece
City	Athens
Period	6/12/16 → 9/12/16

Bibliographical note

-

Access to Document

10.1109/SSCI.2016.7849961

Cite this

@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 = "-; 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016 ; Conference date: 06-12-2016 Through 09-12-2016",

year = "2017",

month = feb,

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",

}

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 publication

AN - SCOPUS:85016042103

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

PB - IEEE

T2 - 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016

Y2 - 6 December 2016 through 9 December 2016

ER -

Offline and online time in Sequential Decision-Making Problems

Abstract

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this