Finite-Time Convergence of Distributionally Robust Q-Learning with Linear Function Approximation

Abstract

Distributionally robust reinforcement learning (DRRL) seeks policies that perform well when the deployment transition model differs from the nominal model generating the data. Most finite-sample guarantees for DRRL are tabular, model-based, rely on generative access, or obtain function-approximation guarantees only under additional structure, such as linear-transition models or restrictive discount-factor conditions. We study discounted model-free robust Q-learning under an $(s,a)$-rectangular chi-square uncertainty set, with linear approximation of the robust Q-function, using only a single Markovian trajectory from an unknown nominal model. Our algorithm combines a target-network outer loop with a dual function-approximation scheme for the chi-square robust Bellman update. The dual procedure uses moment-tracking critics, suffix averaging, a fresh-evaluation stage for the variance-like moment, and a tunable smoothing parameter to have a Lipschitz-continuous chi-square dual gradient. We prove a finite-time convergence bound to the optimal robust Q-function up to approximation error, without imposing a small-discount-factor assumption. Our results help close a gap between the empirical use of robust RL algorithms and the non-asymptotic guarantees available for their non-robust counterparts.