Finite-Sample Analysis of Stochastic Approximation Using Smooth Convex Envelopes

Abstract

Stochastic Approximation (SA) is a popular approach for solving fixed-point equations where the information is corrupted by noise. In this paper, we consider an SA involving a contraction mapping with respect to an arbitrary norm, and show its finite-sample error bounds while using different stepsizes. The idea is to construct a smooth Lyapunov function using the generalized Moreau envelope, and show that the iterates of SA have negative drift with respect to that Lyapunov function. Our result is applicable in Reinforcement Learning (RL). In particular, we use it to establish the first-known convergence rate of the V-trace algorithm for off-policy TD-learning. Moreover, we also use it to study TD-learning in the on-policy setting, and recover the existing state-of-the-art results for $Q$-learning. Importantly, our construction results in only a logarithmic dependence of the convergence bound on the size of the state-space.

References in corpus (5)

• Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving
• Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation for Multi-Agent Reinforcement Learning
• TorchBeast: A PyTorch Platform for Distributed RL
• Finite-Time Analysis of Asynchronous Stochastic Approximation and $Q$-Learning
• Stochastic approximation with cone-contractive operators: Sharp ${\ell }_{\infty }$-bounds for $Q$-learning

Cited by in corpus (6)

• Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model
• Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis
• Finite-Time Analysis for Double Q-learning
• Q-learning with Uniformly Bounded Variance: Large Discounting is Not a Barrier to Fast Learning
• Instance-dependent ${\ell }_{\infty }$-bounds for policy evaluation in tabular reinforcement learning
• Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs