Finite-Sample Analysis of Stochastic Approximation Using Smooth Convex Envelopes
Preprint
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.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Finite-sample analysis of nonlinear stochastic approximation with applications in reinforcement learningAutomatica, 2022
- First-order and Stochastic Optimization Methods for Machine Learning2020
- Markov Chains and Mixing Times2017
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- On lower complexity bounds for large-scale smooth convex optimizationJournal of Complexity, 2015
- Error bounds for constant step-size -learningSystems & Control Letters, 2012
- Convergence Results for Some Temporal Difference Methods Based on Least SquaresIEEE Transactions on Automatic Control, 2009
- Boundedness of iterates in Q-LearningSystems & Control Letters, 2006
- Learning Rates for Q-LearningLecture Notes in Computer Science, 2001
- Average cost temporal-difference learningAutomatica, 1999