Rationally inattentive control of markov processes

Ehsan Shafieepoorfard, Maxim Raginsky, Sean P. Meyn

Research output: Contribution to journalArticlepeer-review

Abstract

The article poses a general model for optimal control subject to information constraints, motivated in part by recent work of Sims and others 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 theory is illustrated through the example of information-constrained linear quadratic Gaussian control problem. Some results on the infinite-horizon discounted-cost criterion are also presented.

Original languageEnglish (US)
Pages (from-to)987-1016
Number of pages30
JournalSIAM Journal on Control and Optimization
Volume54
Issue number2
DOIs
StatePublished - 2016

Keywords

  • Information theory
  • Markov decision processes
  • Observation channels
  • Optimization
  • Stochastic control

ASJC Scopus subject areas

  • Control and Optimization
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Rationally inattentive control of markov processes'. Together they form a unique fingerprint.

Cite this