Stochastic Approximation with Unbounded Markovian Noise: A General-Purpose Theorem

TL;DR

This paper introduces a general theorem for stochastic approximation under unbounded Markovian noise, enabling finite-time analysis of reinforcement learning and optimization algorithms with broad applicability.

Contribution

It provides a versatile black-box theorem for non-linear stochastic approximation with unbounded Markovian noise, extending finite-time bounds to new settings.

Findings

Finite-time bounds for TD learning with linear function approximation.

Improved finite-time bounds for Q-learning with broader policy classes.

First finite-time bounds for distributed stochastic optimization with cyclic block coordinate descent.

Abstract

Motivated by engineering applications such as resource allocation in networks and inventory systems, we consider average-reward Reinforcement Learning with unbounded state space and reward function. Recent works studied this problem in the actor-critic framework and established finite sample bounds assuming access to a critic with certain error guarantees. We complement their work by studying Temporal Difference (TD) learning with linear function approximation and establishing finite-time bounds with the optimal $\mathcal{O}\left(1/\epsilon^2\right)$ sample complexity. These results are obtained using the following general-purpose theorem for non-linear Stochastic Approximation (SA). Suppose that one constructs a Lyapunov function for a non-linear SA with certain drift condition. Then, our theorem establishes finite-time bounds when this SA is driven by unbounded Markovian noise under suitable conditions. It serves as a black box tool to generalize sample guarantees on SA from i.i.d. or martingale difference case to potentially unbounded Markovian noise. The generality and the mild assumption of the setup enables broad applicability of our theorem. We illustrate its power by studying two more systems: (i) We improve upon the finite-time bounds of $Q$-learning by tightening the error bounds and also allowing for a larger class of behavior policies. (ii) We establish the first ever finite-time bounds for distributed stochastic optimization of high-dimensional smooth strongly convex function using cyclic block coordinate descent.