Skip to Main content Skip to Navigation
Journal articles

A Convex Programming Approach for Discrete-Time Markov Decision Processes under the Expected Total Reward Criterion

Abstract : In this work, we study discrete-time Markov decision processes (MDPs) under constraints with Borel state and action spaces and where all the performance functions have the sameform of the expected total reward (ETR) criterion over the infinite time horizon. One of our objective is to propose a convex programming formulation for this type of MDPs. It will be shown that the values of the constrained control problem and thea ssociated convex program coincide and that if there exists an optimal solution to the convex program then there exists a stationary randomized policy which is optimal for the MDP. It will be also shown that in the framework of constrained control problems, the supremum of the expected total rewards over the set of randomized policies is equal to the supremum of the expected total rewards over the set of stationary randomized policies. We consider standard hypotheses such as the so-called continuity-compactness conditions and a Slater-type condition. Our assumptions are quite weak to deal with cases that have not yet been addressed in the literature. An example is presented to illustrate our results with respect to those of the literature.
Document type :
Journal articles
Complete list of metadatas

https://hal.inria.fr/hal-03033727
Contributor : François Dufour <>
Submitted on : Tuesday, December 1, 2020 - 2:55:08 PM
Last modification on : Wednesday, December 2, 2020 - 11:58:51 AM

Links full text

Identifiers

Collections

Citation

François Dufour, Alexandre Genadot. A Convex Programming Approach for Discrete-Time Markov Decision Processes under the Expected Total Reward Criterion. SIAM Journal on Control and Optimization, Society for Industrial and Applied Mathematics, 2020, 58 (4), pp.2535-2566. ⟨10.1137/19M1255811⟩. ⟨hal-03033727⟩

Share

Metrics

Record views

12