Papers › Policy Gradient for Robust Markov Decision Processes

Policy Gradient for Robust Markov Decision Processes

29 Oct 2024arXiv:2410.22114archive 2025-07-28

Qiuhao Wang, Shaohang Xu, Chin Pang Ho, Marek Petrik

We develop a generic policy gradient method with the global optimality guarantee for robust Markov Decision Processes (MDPs). While policy gradient methods are widely used for solving dynamic decision problems due to their scalable and efficient nature, adapting these methods to account for model ambiguity has been challenging, often making it impractical to learn robust policies. This paper introduces a novel policy gradient method, Double-Loop Robust Policy Mirror Descent (DRPMD), for solving robust MDPs. DRPMD employs a general mirror descent update rule for the policy optimization with adaptive tolerance per iteration, guaranteeing convergence to a globally optimal policy. We provide a comprehensive analysis of DRPMD, including new convergence results under both direct and softmax parameterizations, and provide novel insights into the inner problem solution through Transition Mirror Ascent (TMA). Additionally, we propose innovative parametric transition kernels for both discrete and continuous state-action spaces, broadening the applicability of our approach. Empirical results validate the robustness and global convergence of DRPMD across various challenging robust MDP settings.

PaperPDFCode

Code

JerrisonWang/JMLR-DRPMD officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Policy Gradient Methods

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Softmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections