Rational inattention in controlled Markov processes

Ehsan Shafieepoorfard; Maxim Raginsky; Sean P. Meyn

doi:10.1109/acc.2013.6580906

Rational inattention in controlled Markov processes

Ehsan Shafieepoorfard, Maxim Raginsky, Sean P. Meyn

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The paper poses a general model for optimal control subject to information constraints, motivated in part by recent work on information-constrained decision-making by economic agents. In the average-cost optimal control framework, the general model introduced in this paper reduces to a variant of the linear-programming representation of the average-cost optimal control problem, subject to an additional mutual information constraint on the randomized stationary policy. The resulting optimization problem is convex and admits a decomposition based on the Bellman error, which is the object of study in approximate dynamic programming. The structural results presented in this paper can be used to obtain performance bounds, as well as algorithms for computation or approximation of optimal policies.

Original language	English (US)
Title of host publication	2013 American Control Conference, ACC 2013
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	6790-6797
Number of pages	8
ISBN (Print)	9781479901777
DOIs	https://doi.org/10.1109/acc.2013.6580906
State	Published - 2013
Event	2013 1st American Control Conference, ACC 2013 - Washington, DC, United States Duration: Jun 17 2013 → Jun 19 2013

Publication series

Name	Proceedings of the American Control Conference
ISSN (Print)	0743-1619

Other

Other	2013 1st American Control Conference, ACC 2013
Country/Territory	United States
City	Washington, DC
Period	6/17/13 → 6/19/13

ASJC Scopus subject areas

Electrical and Electronic Engineering

Online availability

10.1109/acc.2013.6580906

Library availability

Discover UIUC Full Text

Cite this

Rational inattention in controlled Markov processes. / Shafieepoorfard, Ehsan; Raginsky, Maxim; Meyn, Sean P.
2013 American Control Conference, ACC 2013. Institute of Electrical and Electronics Engineers Inc., 2013. p. 6790-6797 6580906 (Proceedings of the American Control Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Shafieepoorfard, E, Raginsky, M & Meyn, SP 2013, Rational inattention in controlled Markov processes. in 2013 American Control Conference, ACC 2013., 6580906, Proceedings of the American Control Conference, Institute of Electrical and Electronics Engineers Inc., pp. 6790-6797, 2013 1st American Control Conference, ACC 2013, Washington, DC, United States, 6/17/13. https://doi.org/10.1109/acc.2013.6580906

@inproceedings{78b84b0c3e58465fafedfb2f630258df,

title = "Rational inattention in controlled Markov processes",

abstract = "The paper poses a general model for optimal control subject to information constraints, motivated in part by recent work on information-constrained decision-making by economic agents. In the average-cost optimal control framework, the general model introduced in this paper reduces to a variant of the linear-programming representation of the average-cost optimal control problem, subject to an additional mutual information constraint on the randomized stationary policy. The resulting optimization problem is convex and admits a decomposition based on the Bellman error, which is the object of study in approximate dynamic programming. The structural results presented in this paper can be used to obtain performance bounds, as well as algorithms for computation or approximation of optimal policies.",

author = "Ehsan Shafieepoorfard and Maxim Raginsky and Meyn, {Sean P.}",

year = "2013",

doi = "10.1109/acc.2013.6580906",

language = "English (US)",

isbn = "9781479901777",

series = "Proceedings of the American Control Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "6790--6797",

booktitle = "2013 American Control Conference, ACC 2013",

address = "United States",

note = "2013 1st American Control Conference, ACC 2013 ; Conference date: 17-06-2013 Through 19-06-2013",

}

TY - GEN

T1 - Rational inattention in controlled Markov processes

AU - Shafieepoorfard, Ehsan

AU - Raginsky, Maxim

AU - Meyn, Sean P.

PY - 2013

Y1 - 2013

N2 - The paper poses a general model for optimal control subject to information constraints, motivated in part by recent work on information-constrained decision-making by economic agents. In the average-cost optimal control framework, the general model introduced in this paper reduces to a variant of the linear-programming representation of the average-cost optimal control problem, subject to an additional mutual information constraint on the randomized stationary policy. The resulting optimization problem is convex and admits a decomposition based on the Bellman error, which is the object of study in approximate dynamic programming. The structural results presented in this paper can be used to obtain performance bounds, as well as algorithms for computation or approximation of optimal policies.

AB - The paper poses a general model for optimal control subject to information constraints, motivated in part by recent work on information-constrained decision-making by economic agents. In the average-cost optimal control framework, the general model introduced in this paper reduces to a variant of the linear-programming representation of the average-cost optimal control problem, subject to an additional mutual information constraint on the randomized stationary policy. The resulting optimization problem is convex and admits a decomposition based on the Bellman error, which is the object of study in approximate dynamic programming. The structural results presented in this paper can be used to obtain performance bounds, as well as algorithms for computation or approximation of optimal policies.

UR - http://www.scopus.com/inward/record.url?scp=84883547631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883547631&partnerID=8YFLogxK

U2 - 10.1109/acc.2013.6580906

DO - 10.1109/acc.2013.6580906

M3 - Conference contribution

AN - SCOPUS:84883547631

SN - 9781479901777

T3 - Proceedings of the American Control Conference

SP - 6790

EP - 6797

BT - 2013 American Control Conference, ACC 2013

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2013 1st American Control Conference, ACC 2013

Y2 - 17 June 2013 through 19 June 2013

ER -

Rational inattention in controlled Markov processes

Abstract

Publication series

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this