Rationally inattentive control of Markov processes

2015/02/12 by Shafieepoorfard, Ehsan, Raginsky, Maxim, Meyn, Sean P. · 1 citation
#90C40 #90C47 #94A34 #FOS: Computer and information sciences #FOS: Mathematics #Information Theory (cs.IT) #Optimization and Control (math.OC)

paper · doi:10.48550/arxiv.1502.03762

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 (LQG) control problem. Some results on the infinite-horizon discounted-cost criterion are also presented.

Cited by

• Deceptive Planning Exploiting Inattention Blindness

Related

• On Optimal Control of Discounted Cost Infinite-Horizon Markov Decision Processes Under Local State Information Structures
• On Robust Control of Partially Observed Uncertain Systems with Additive Costs
• LQG Control with Minimum Directed Information: Semidefinite Programming Approach
• Optimal Control with Noisy Time
• Another Look at Partially Observed Optimal Stochastic Control: Existence, Ergodicity, and Approximations without Belief-Reduction