Stochastic Shortest Path with Energy Constraints in POMDPs:
(Extended Abstract)

D 2016

Stochastic Shortest Path with Energy Constraints in POMDPs: (Extended Abstract)

BRÁZDIL, Tomáš, Petr NOVOTNÝ, Krishnendu CHATTERJEE, Martin CHMELÍK, Anchit GUPTA et. al.

Basic information

Original name

Stochastic Shortest Path with Energy Constraints in POMDPs: (Extended Abstract)

Authors

BRÁZDIL, Tomáš (203 Czech Republic, guarantor, belonging to the institution), Petr NOVOTNÝ (203 Czech Republic), Krishnendu CHATTERJEE (356 India), Martin CHMELÍK (203 Czech Republic) and Anchit GUPTA (356 India)

Edition

Singapur, Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems, p. 1465-1466, 2 pp. 2016

Publisher

ACM

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

RIV identification code

RIV/00216224:14330/16:00088501

Organization unit

Faculty of Informatics

ISBN

978-1-4503-4239-1

UT WoS

000465199800247

Keywords in English

POMDP; planning; energy constraints; decision trees

Abstract

V originále

We extend the traditional framework of POMDPs to model resource consumption inducing a hard constraint on the behaviour of the model. Resource levels increase and decrease with transitions, and the hard constraint requires that the level remains positive in all steps. We present an algorithm for solving POMDPs with resource levels, developing on existing POMDP solvers. Our second contribution is related to policy representation. For larger POMDPs the policies computed by existing solvers are too large to be understandable, an issue particularly pronounced in POMDPs with resource levels. We present a procedure based on machine learning techniques that extracts important decisions of a policy and outputs its readable representation.

Links

GBP202/12/G061, research and development project

Name: Centrum excelence - Institut teoretické informatiky (CE-ITI) (Acronym: CE-ITI)

Investor: Czech Science Foundation

Citovat

BRÁZDIL, Tomáš, Petr NOVOTNÝ, Krishnendu CHATTERJEE, Martin CHMELÍK and Anchit GUPTA. Stochastic Shortest Path with Energy Constraints in POMDPs: (Extended Abstract). In Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems. Singapur: ACM, 2016, p. 1465-1466. ISBN 978-1-4503-4239-1.

@inproceedings{1366476,
   author = {Brázdil, Tomáš and Novotný, Petr and Chatterjee, Krishnendu and Chmelík, Martin and Gupta, Anchit},
   address = {Singapur},
   booktitle = {Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems},
   keywords = {POMDP; planning; energy constraints; decision trees},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Singapur},
   isbn = {978-1-4503-4239-1},
   pages = {1465-1466},
   publisher = {ACM},
   title = {Stochastic Shortest Path with Energy Constraints in POMDPs: (Extended Abstract)},
   year = {2016}
}

TY  - JOUR
ID  - 1366476
AU  - Brázdil, Tomáš - Novotný, Petr - Chatterjee, Krishnendu - Chmelík, Martin - Gupta, Anchit
PY  - 2016
TI  - Stochastic Shortest Path with Energy Constraints in POMDPs: (Extended Abstract)
PB  - ACM
CY  - Singapur
SN  - 9781450342391
KW  - POMDP
KW  - planning
KW  - energy constraints
KW  - decision trees
N2  - We extend the traditional framework of POMDPs to model resource consumption inducing a hard constraint on the behaviour of the model. Resource levels increase and decrease with transitions, and the hard constraint requires that the level remains positive in all steps. We present an algorithm for solving POMDPs with resource levels, developing on existing POMDP solvers. Our second contribution is related to policy representation. For larger POMDPs the policies computed by existing solvers are too large to be understandable, an issue particularly pronounced in POMDPs with resource levels. We present a procedure based on machine learning techniques that extracts important decisions of a policy and outputs its readable representation.
ER  -

BRÁZDIL, Tomáš, Petr NOVOTNÝ, Krishnendu CHATTERJEE, Martin CHMELÍK and Anchit GUPTA. Stochastic Shortest Path with Energy Constraints in POMDPs: (Extended Abstract). In \textit{Proceedings of the 2016 International Conference on Autonomous Agents \&{} Multiagent Systems}. Singapur: ACM, 2016, p.~1465-1466. ISBN~978-1-4503-4239-1.

Detailed Information on Publication Record