English
Related papers

Related papers: A Concentration Bound for TD(0) with Function Appr…

200 papers

We study weighted Tikhonov regularization for large-scale linear discrete ill-posed problems with random noise. Under a polynomial upper-bound assumption on the generalized eigenvalues of the discrete forward operator, we derive stochastic…

Numerical Analysis · Mathematics 2026-05-19 Duan-Peng Ling , Wenlong Zhang

Temporal difference (TD) learning with linear function approximation (linear TD) is a classic and powerful prediction algorithm in reinforcement learning. While it is well-understood that linear TD converges almost surely to a unique point,…

Machine Learning · Computer Science 2026-03-25 Jiuqi Wang , Shangtong Zhang

We propose a stochastic approximation (SA) based method with randomization of samples for policy evaluation using the least squares temporal difference (LSTD) algorithm. Our proposed scheme is equivalent to running regular temporal…

Machine Learning · Computer Science 2020-01-27 L. A. Prashanth , Nathaniel Korda , Rémi Munos

This paper considers a novel multi-agent linear stochastic approximation algorithm driven by Markovian noise and general consensus-type interaction, in which each agent evolves according to its local stochastic approximation process which…

Machine Learning · Computer Science 2023-10-02 Yixuan Lin , Vijay Gupta , Ji Liu

This paper presents a finite time convergence analysis for a decentralized stochastic approximation (SA) scheme. The scheme generalizes several algorithms for decentralized machine learning and multi-agent reinforcement learning. Our proof…

Optimization and Control · Mathematics 2020-11-06 Hoi-To Wai

The martingale method is used to establish concentration inequalities for a class of dependent random sequences on a countable state space, with the constants in the inequalities expressed in terms of certain mixing coefficients. Along the…

Probability · Mathematics 2009-01-22 Leonid , Kontorovich , Kavita Ramanan

We present the first uniform-in-time high-probability bound for SGD under the PL condition, where the gradient noise contains both Markovian and martingale difference components. This significantly broadens the scope of finite-time…

Machine Learning · Computer Science 2026-03-17 Avik Kar , Siddharth Chandak , Rahul Singh , Eric Moulines , Shalabh Bhatnagar , Nicholas Bambos

Relative temporal-difference (TD) learning was introduced to mitigate the slow convergence of TD methods when the discount factor approaches one by subtracting a baseline from the temporal-difference update. While this idea has been studied…

Machine Learning · Computer Science 2026-04-08 Masoud S. Sakha , Rushikesh Kamalapurkar , Sean Meyn

In this paper, we establish non-asymptotic bounds for accuracy of normal approximation for linear two-timescale stochastic approximation (TTSA) algorithms driven by martingale difference or Markov noise. Focusing on both the last iterate…

Machine Learning · Statistics 2025-12-10 Bogdan Butyrin , Artemy Rubtsov , Alexey Naumov , Vladimir Ulyanov , Sergey Samsonov

Value functions derived from Markov decision processes arise as a central component of algorithms as well as performance metrics in many statistics and engineering applications of machine learning techniques. Computation of the solution to…

Machine Learning · Computer Science 2020-03-02 Adithya M. Devraj , Ioannis Kontoyiannis , Sean P. Meyn

Motivated by the study of $Q$-learning algorithms in reinforcement learning, we study a class of stochastic approximation procedures based on operators that satisfy monotonicity and quasi-contractivity conditions with respect to an…

Machine Learning · Computer Science 2019-06-25 Martin J. Wainwright

We consider additive functionals of Markov processes in continuous time with general (metric) state spaces. We derive concentration bounds for their exponential moments and moments of finite order. Applications include diffusions,…

Probability · Mathematics 2022-02-18 Frank Redig , Florian Völlering

The average reward is a fundamental performance metric in reinforcement learning (RL) focusing on the long-run performance of an agent. Differential temporal difference (TD) learning algorithms are a major advance for average reward RL as…

Machine Learning · Computer Science 2026-02-19 Ethan Blaser , Jiuqi Wang , Shangtong Zhang

Motivated by applications in reinforcement learning (RL), we study a nonlinear stochastic approximation (SA) algorithm under Markovian noise, and establish its finite-sample convergence bounds under various stepsizes. Specifically, we show…

Optimization and Control · Mathematics 2022-01-27 Zaiwei Chen , Sheng Zhang , Thinh T. Doan , John-Paul Clarke , Siva Theja Maguluri

Value functions arise as a component of algorithms as well as performance metrics in statistics and engineering applications. Computation of the associated Bellman equations is numerically challenging in all but a few special cases. A…

Systems and Control · Computer Science 2018-12-27 Adithya M. Devraj , Sean P. Meyn

This paper concerns quasi-stochastic approximation (QSA) to solve root finding problems commonly found in applications to optimization and reinforcement learning. The general constant gain algorithm may be expressed as the…

Optimization and Control · Mathematics 2024-04-02 Caio Kalil Lauand , Sean Meyn

Poisson's equation has a lot of applications in various areas. Usually it is hard to derive the explicit expression of the solution of Poisson's equation for a Markov chain on an infinitely many state space. We will present a computational…

Probability · Mathematics 2021-01-05 Jinpeng Liu , Yuanyuan Liu , Yiqiang Q. Zhao

We consider the problem of estimating the asymptotic variance of a function defined on a Markov chain, an important step for statistical inference of the stationary mean. We design a novel recursive estimator that requires $O(1)$…

Statistics Theory · Mathematics 2024-09-24 Shubhada Agrawal , Prashanth L. A. , Siva Theja Maguluri

The paper is concerned with the equilibrium distributions of continuous-time density dependent Markov processes on the integers. These distributions are known typically to be approximately normal, and the approximation error, as measured in…

Probability · Mathematics 2009-02-06 Sanda N. Socoll , A. D. Barbour

We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by `controlled' Markov noise. In particular, both the faster and slower recursions have non-additive controlled Markov noise…

Dynamical Systems · Mathematics 2017-02-28 Prasenjit Karmakar , Shalabh Bhatnagar