AI RESEARCH
Convergence of Distributionally Robust Q-Learning with Linear Function Approximation
arXiv CS.LG
•
ArXi:2510.01721v2 Announce Type: replace Distributionally robust reinforcement learning (DRRL) focuses on designing policies that achieve good performance under model uncertainties. The goal is to maximize the worst-case long-term discounted reward, where the data for RL comes from a nominal model while the deployed environment can deviate from the nominal model within a prescribed uncertainty set. Existing convergence guarantees for DRRL are limited to tabular MDPs or are dependent on restrictive discount factor assumptions when function approximation is used.