English
Related papers

Related papers: A Statistical Analysis of Polyak-Ruppert Averaged …

200 papers

We present a non-asymptotic convergence analysis of $Q$-learning and actor-critic algorithms for robust average-reward Markov Decision Processes (MDPs) under contamination, total-variation (TV) distance, and Wasserstein uncertainty sets. A…

Machine Learning · Computer Science 2025-12-11 Yang Xu , Swetha Ganesh , Vaneet Aggarwal

In this paper, we obtain the Berry-Esseen bound for multivariate normal approximation for the Polyak-Ruppert averaged iterates of the linear stochastic approximation (LSA) algorithm with decreasing step size. Moreover, we prove the…

Machine Learning · Statistics 2025-02-04 Sergey Samsonov , Eric Moulines , Qi-Man Shao , Zhuo-Song Zhang , Alexey Naumov

This paper is devoted to the non-asymptotic control of the mean-squared error for the Ruppert-Polyak stochastic averaged gradient descent introduced in the seminal contributions of [Rup88] and [PJ92]. In our main results, we establish…

Statistics Theory · Mathematics 2017-09-12 Sébastien Gadat , Fabien Panloup

This paper applies the authors' recent results on asynchronous stochastic approximation (SA) in the Borkar-Meyn framework to reinforcement learning in average-reward semi-Markov decision processes (SMDPs). We establish the convergence of an…

Machine Learning · Computer Science 2025-12-09 Huizhen Yu , Yi Wan , Richard S. Sutton

In this paper, we establish a theoretical comparison between the asymptotic mean-squared error of Double Q-learning and Q-learning. Our result builds upon an analysis for linear stochastic approximation based on Lyapunov equations and…

Machine Learning · Computer Science 2022-06-16 Wentao Weng , Harsh Gupta , Niao He , Lei Ying , R. Srikant

While Bayesian-based exploration often demonstrates superior empirical performance compared to bonus-based methods in model-based reinforcement learning (RL), its theoretical understanding remains limited for model-free settings. Existing…

Machine Learning · Computer Science 2026-02-05 He Wang , Xingyu Xu , Yuejie Chi

This paper investigates the continuous-time counterpart of the Q-function for entropy-regularized mean-field control (MFC) with controlled common noise, coined as q-function by Jia and Zhou (2023) in the single agent's model. We first show…

Optimization and Control · Mathematics 2026-05-01 Zhenjie Ren , Xiaoli Wei , Xiang Yu , Xun Yu Zhou

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 random integer partitions $\lambda$ that follow the Poissonized Plancherel measure of parameter $t^2$. Using Riemann$-$Hilbert techniques, we establish the asymptotics of the multiplicative averages $$Q(t,s)=\mathbb{E} \left[…

Mathematical Physics · Physics 2026-01-30 Mattia Cafasso , Matteo Mucciconi , Giulio Ruzza

We study the continuous-time counterpart of Q-learning for reinforcement learning (RL) under the entropy-regularized, exploratory diffusion process formulation introduced by Wang et al. (2020). As the conventional (big) Q-function collapses…

Machine Learning · Computer Science 2025-05-07 Yanwei Jia , Xun Yu Zhou

Watkins' and Dayan's Q-learning is a model-free reinforcement learning algorithm that iteratively refines an estimate for the optimal action-value function of an MDP by stochastically "visiting" many state-ation pairs [Watkins and Dayan,…

Machine Learning · Computer Science 2021-08-09 Matthew T. Regehr , Alex Ayoub

Q-functions are widely used in discrete-time learning and control to model future costs arising from a given control policy, when the initial state and input are given. Although some of their properties are understood, Q-functions…

Optimization and Control · Mathematics 2019-02-21 Joseph Warrington

A fundamental question in the theory of reinforcement learning is: suppose the optimal $Q$-function lies in the linear span of a given $d$ dimensional feature mapping, is sample-efficient reinforcement learning (RL) possible? The recent and…

Machine Learning · Computer Science 2021-10-22 Yuanhao Wang , Ruosong Wang , Sham M. Kakade

Soft Q-learning is a variation of Q-learning designed to solve entropy regularized Markov decision problems where an agent aims to maximize the entropy regularized value function. Despite its empirical success, there have been limited…

Machine Learning · Computer Science 2024-09-06 Narim Jeong , Donghwan Lee

We consider a reinforcement learning setting in which the deployment environment is different from the training environment. Applying a robust Markov decision processes formulation, we extend the distributionally robust $Q$-learning…

Machine Learning · Computer Science 2024-08-02 Shengbo Wang , Nian Si , Jose Blanchet , Zhengyuan Zhou

The recently successful Munchausen Reinforcement Learning (M-RL) features implicit Kullback-Leibler (KL) regularization by augmenting the reward function with logarithm of the current stochastic policy. Though significant improvement has…

Machine Learning · Computer Science 2022-05-17 Lingwei Zhu , Zheng Chen , Eiji Uchibe , Takamitsu Matsubara

In reinforcement learning (RL), Q-learning is a fundamental algorithm whose convergence is guaranteed in the tabular setting. However, this convergence guarantee does not hold under linear function approximation. To overcome this…

Machine Learning · Computer Science 2026-02-04 Hyukjun Yang , Han-Dong Lim , Donghwan Lee

We consider linear two-time-scale stochastic approximation algorithms driven by martingale noise. Recent applications in machine learning motivate the need to understand finite-time error rates, but conventional stochastic approximation…

Machine Learning · Computer Science 2025-12-12 Seo Taek Kong , Sihan Zeng , Thinh T. Doan , R. Srikant

We give tight statistical query (SQ) lower bounds for learnining halfspaces in the presence of Massart noise. In particular, suppose that all labels are corrupted with probability at most $\eta$. We show that for arbitrary $\eta \in…

Machine Learning · Computer Science 2022-01-25 Rajai Nasser , Stefan Tiegel

We study how a central bank should dynamically set short-term nominal interest rates to stabilize inflation and unemployment when macroeconomic relationships are uncertain and time-varying. We model monetary policy as a sequential…

Statistical Finance · Quantitative Finance 2026-01-06 Tony Wang , Kyle Feinstein , Sheryl Chen