paper-with-me

Papers

Almost Sure Convergence Rates and Concentration of Stochastic Approximation and Reinforcement Learning with Markovian Noise

2024-11-20 · Xiaochi Qian, Zixuan Xie, Xinyu Liu, Shangtong Zhang

This paper establishes the first almost sure convergence rate and the first maximal concentration bound with exponential tails for general contractive stochastic approximation algorithms with Markovian noise. As a corollary, we also obtain convergence rates in $L^p$. Key to our successes is a novel discretization of the mean ODE of stochastic approximation algorithms using intervals with diminishing (instead of constant) length. As applications, we provide the first almost sure convergence rate for $Q$-learning with Markovian samples without count-based learning rates. We also provide the first concentration bound for off-policy temporal difference learning with Markovian samples.

📄 PDF Abstract BibTeX arXiv:2411.13711

Code (0)

등록된 구현이 없습니다.

Tasks

Q-Learning

Similar Papers 제목 키워드 기반

Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning

2025-09-30 · Xinyu Liu, Zixuan Xie, Shangtong Zhang arxiv

The Robbins-Siegmund theorem establishes the convergence of stochastic processes that are almost supermartingales and is one of the most commonly used approaches for analyzing stochastic iterative algorithms in stochasti…

Reinforcement Learning

On Almost Sure Convergence Rates of Stochastic Gradient Methods

2022-02-09 · Jun Liu, Ye Yuan

The vast majority of convergence rates analysis for stochastic gradient methods in the literature focus on convergence in expectation, whereas trajectory-wise almost sure convergence is clearly important to ensure that a…

Accelerated Almost-Sure Convergence Rates for Nonconvex Stochastic Gradient Descent using Stochastic Learning Rates

2021-10-25 · Theodoros Mamalis, Dusan Stipanovic, Petros Voulgaris

Large-scale optimization problems require algorithms both effective and efficient. One such popular and proven algorithm is Stochastic Gradient Descent which uses first-order gradient information to solve these problems.…

Almost sure convergence rates for Stochastic Gradient Descent and Stochastic Heavy Ball

2020-06-14 · Othmane Sebbouh, Robert M. Gower, Aaron Defazio

We study stochastic gradient descent (SGD) and the stochastic heavy ball method (SHB, otherwise known as the momentum method) for the general stochastic approximation problem. For SGD, in the convex and smooth setting, w…

Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift

2026-05-08 · Xinyu Liu, Zixuan Xie, Shangtong Zhang arxiv

Establishing almost sure convergence rates for stochastic approximation and reinforcement learning under Markovian noise is a fundamental theoretical challenge. We make progress towards this challenge for a class of stoc…

Reinforcement Learning