English
Related papers

Related papers: On TD(0) with function approximation: Concentratio…

200 papers

This paper analyses a $(1,\lambda)$-Evolution Strategy, a randomised comparison-based adaptive search algorithm, on a simple constraint optimisation problem. The algorithm uses resampling to handle the constraint and optimizes a linear…

Neural and Evolutionary Computing · Computer Science 2014-12-09 Alexandre Chotard , Anne Auger , Nikolaus Hansen

One of the most basic problems in reinforcement learning (RL) is policy evaluation: estimating the long-term return, i.e., value function, corresponding to a given fixed policy. The celebrated Temporal Difference (TD) learning algorithm…

Machine Learning · Computer Science 2025-02-10 Sreejeet Maity , Aritra Mitra

Recent non-asymptotic analyses have substantially advanced the theory of distributional policy evaluation, but they largely concern synchronous full-state updates under a generative model, model-based estimators, accelerated variants, or…

Machine Learning · Computer Science 2026-05-11 Ege C. Kaya , Abolfazl Hashemi

In this paper we propose several novel distributed gradient-based temporal difference algorithms for multi-agent off-policy learning of linear approximation of the value function in Markov decision processes with strict information…

Machine Learning · Computer Science 2021-04-20 Milos S. Stankovic , Marko Beko , Srdjan S. Stankovic

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

It is still common to use Q-learning and temporal difference (TD) learning-even though they have divergence issues and sound Gradient TD alternatives exist-because divergence seems rare and they typically perform well. However, recent work…

Machine Learning · Computer Science 2020-09-21 Sina Ghiassian , Andrew Patterson , Shivam Garg , Dhawal Gupta , Adam White , Martha White

While much progress has been achieved over the last decades in neuro-inspired machine learning, there are still fundamental theoretical problems in gradient-based learning using combinations of neurons. These problems, such as saddle points…

Machine Learning · Computer Science 2023-06-16 Winfried Lohmiller , Philipp Gassert , Jean-Jacques Slotine

We initiate the study of federated reinforcement learning under environmental heterogeneity by considering a policy evaluation problem. Our setup involves $N$ agents interacting with environments that share the same state and action space…

Machine Learning · Computer Science 2024-07-02 Han Wang , Aritra Mitra , Hamed Hassani , George J. Pappas , James Anderson

Two-timescale Stochastic Approximation (SA) algorithms are widely used in Reinforcement Learning (RL). Their iterates have two parts that are updated using distinct stepsizes. In this work, we develop a novel recipe for their finite sample…

Artificial Intelligence · Computer Science 2018-06-06 Gal Dalal , Balazs Szorenyi , Gugan Thoppe , Shie Mannor

In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms. Previous analyses of this class of algorithms use ODE techniques to prove asymptotic convergence, and to the best of our…

Machine Learning · Computer Science 2020-07-06 Bo Liu , Ji Liu , Mohammad Ghavamzadeh , Sridhar Mahadevan , Marek Petrik

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…

Machine Learning · Computer Science 2024-11-22 Xiaochi Qian , Zixuan Xie , Xinyu Liu , Shangtong Zhang

We study the approximation of a Markov chain on a reduced state space, for both discrete- and continuous-time Markov chains. In this context, we extend the existing theory of formal error bounds for the approximated transient distributions.…

Probability · Mathematics 2025-02-12 Fabian Michel , Markus Siegle

Dynamic Programming suffers from the curse of dimensionality due to large state and action spaces, a challenge further compounded by uncertainties in the environment. To mitigate these issue, we explore an off-policy based Temporal…

Systems and Control · Electrical Eng. & Systems 2025-03-05 Ali Forootani , Raffaele Iervolino , Massimo Tipaldi , Mohammad Khosravi

We study problem-dependent rates, i.e., generalization errors that scale near-optimally with the variance, the effective loss, or the gradient norms evaluated at the "best hypothesis." We introduce a principled framework dubbed "uniform…

Machine Learning · Statistics 2020-12-25 Yunbei Xu , Assaf Zeevi

Two timescale stochastic approximation (SA) has been widely used in value-based reinforcement learning algorithms. In the policy evaluation setting, it can model the linear and nonlinear temporal difference learning with gradient correction…

Machine Learning · Computer Science 2020-11-11 Tengyu Xu , Yingbin Liang

The effectiveness of non-parametric, kernel-based methods for function estimation comes at the price of high computational complexity, which hinders their applicability in adaptive, model-based control. Motivated by approximation techniques…

Statistics Theory · Mathematics 2023-03-17 Anna Scampicchio , Elena Arcari , Melanie N. Zeilinger

We investigate the modeling and the numerical solution of machine learning problems with prediction functions which are linear combinations of elements of a possibly infinite-dimensional dictionary. We propose a novel flexible composite…

Statistics Theory · Mathematics 2015-12-03 Patrick L. Combettes , Saverio Salzo , Silvia Villa

We investigate the statistical and computational limits of latent Diffusion Transformers (DiTs) under the low-dimensional linear latent space assumption. Statistically, we study the universal approximation and sample complexity of the DiTs…

Machine Learning · Statistics 2024-11-01 Jerry Yao-Chieh Hu , Weimin Wu , Zhao Song , Han Liu

We derive an equation for temporal difference learning from statistical principles. Specifically, we start with the variational principle and then bootstrap to produce an updating rule for discounted state value estimates. The resulting…

Machine Learning · Computer Science 2008-11-03 Marcus Hutter , Shane Legg

We present an algorithm based on posterior sampling (aka Thompson sampling) that achieves near-optimal worst-case regret bounds when the underlying Markov Decision Process (MDP) is communicating with a finite, though unknown, diameter. Our…

Machine Learning · Computer Science 2020-04-01 Shipra Agrawal , Randy Jia