English

Approximate Constrained Discounted Dynamic Programming with Uniform Feasibility and Optimality

Optimization and Control 2023-08-08 v1

Abstract

We consider a dynamic programming (DP) approach to approximately solving an infinite-horizon constrained Markov decision process (CMDP) problem with a fixed initial-state for the expected total discounted-reward criterion with a uniform-feasibility constraint of the expected total discounted-cost in a deterministic, history-independent, and stationary policy set. We derive a DP-equation that recursively holds for a CMDP problem and its sub-CMDP problems, where each problem, induced from the parameters of the original CMDP problem, admits a uniformly-optimal feasible policy in its policy set associated with the inputs to the problem. A policy constructed from the DP-equation is shown to achieve the optimal values, defined for the CMDP problem the policy is a solution to, at all states. Based on the result, we discuss off-line and on-line computational algorithms, motivated from policy iteration for MDPs, whose output sequences have local convergences for the original CMDP problem.

Keywords

Cite

@article{arxiv.2308.03297,
  title  = {Approximate Constrained Discounted Dynamic Programming with Uniform Feasibility and Optimality},
  author = {Hyeong Soo Chang},
  journal= {arXiv preprint arXiv:2308.03297},
  year   = {2023}
}
R2 v1 2026-06-28T11:49:27.546Z