English
Related papers

Related papers: A Non-asymptotic Analysis of Non-parametric Tempor…

200 papers

Given a dataset on actions and resulting long-term rewards, a direct estimation approach fits value functions that minimize prediction error on the training data. Temporal difference learning (TD) methods instead fit value functions by…

Machine Learning · Computer Science 2024-02-15 David Cheikhi , Daniel Russo

We study non-parametric estimation of the value function of an infinite-horizon $\gamma$-discounted Markov reward process (MRP) using observations from a single trajectory. We provide non-asymptotic guarantees for a general family of…

Machine Learning · Statistics 2022-11-09 Yaqi Duan , Martin J. Wainwright

We propose a decentralized online learning algorithm for distributed random inverse problems over network graphs with online measurements, and unifies the distributed parameter estimation in Hilbert spaces and the least mean square problem…

Machine Learning · Computer Science 2026-04-09 Xiwei Zhang , Tao Li , Yan Chen , Qianyuan Long

Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable,…

We provide a new non-asymptotic analysis of distributed temporal difference learning with linear function approximation. Our approach relies on ``one-shot averaging,'' where $N$ agents run identical local copies of the TD(0) method and…

Machine Learning · Computer Science 2023-05-26 Rui Liu , Alex Olshevsky

Modeling dynamical systems with ordinary differential equations implies a mechanistic view of the process underlying the dynamics. However in many cases, this knowledge is not available. To overcome this issue, we introduce a general…

Machine Learning · Computer Science 2014-11-20 Markus Heinonen , Florence d'Alché-Buc

In reinforcement learning, temporal difference (TD) is the most direct algorithm to learn the value function of a policy. For large or infinite state spaces, exact representations of the value function are usually not available, and it must…

Machine Learning · Computer Science 2018-05-03 Yann Ollivier

We study the finite-time convergence of TD learning with linear function approximation under Markovian sampling. Existing proofs for this setting either assume a projection step in the algorithm to simplify the analysis, or require a fairly…

Machine Learning · Computer Science 2024-06-27 Aritra Mitra

We consider policy evaluation in infinite-horizon discounted Markov decision problems (MDPs) with infinite spaces. We reformulate this task a compositional stochastic program with a function-valued decision variable that belongs to a…

Optimization and Control · Mathematics 2020-05-19 Alec Koppel , Garrett Warnell , Ethan Stump , Peter Stone , Alejandro Ribeiro

Under mild assumptions on the kernel, we obtain the best known error rates in a regularized learning scenario taking place in the corresponding reproducing kernel Hilbert space (RKHS). The main novelty in the analysis is a proof that one…

Statistics Theory · Mathematics 2010-01-14 Shahar Mendelson , Joseph Neeman

In this paper, we present an efficient algorithm for solving a class of chance constrained optimization under non-parametric uncertainty. Our algorithm is built on the possibility of representing arbitrary distributions as functions in…

Robotics · Computer Science 2018-11-26 Bharath Gopalakrishnan , Arun Kumar Singh , K. Madhava Krishna , Dinesh Manocha

We are interested in understanding stability (almost sure boundedness) of stochastic approximation algorithms (SAs) driven by a `controlled Markov' process. Analyzing this class of algorithms is important, since many reinforcement learning…

Systems and Control · Computer Science 2018-05-18 Arunselvan Ramaswamy , Shalabh Bhatnagar

In this paper we investigate the problem of learning an unknown bounded function. We be emphasize special cases where it is possible to provide very simple (in terms of computation) estimates enjoying in addition the property of being…

Statistics Theory · Mathematics 2007-06-13 Gerard Kerkyacharian , Dominique Picard

Statistical machine learning plays an important role in modern statistics and computer science. One main goal of statistical machine learning is to provide universally consistent algorithms, i.e., the estimator converges in probability or…

Machine Learning · Statistics 2016-04-18 Andreas Christmann , Florian Dumpert , Dao-Hong Xiang

This paper studies convergence of empirical risks in reproducing kernel Hilbert spaces (RKHS). A conventional assumption in the existing research is that empirical training data do not contain any noise but this may not be satisfied in some…

Optimization and Control · Mathematics 2020-05-19 Shaoyan Guo , Huifu Xu , Liwei Zhang

We propose a new, nonparametric approach to learning and representing transition dynamics in Markov decision processes (MDPs), which can be combined easily with dynamic programming methods for policy optimisation and value estimation. This…

Machine Learning · Computer Science 2012-06-22 Steffen Grunewalder , Guy Lever , Luca Baldassarre , Massi Pontil , Arthur Gretton

We establish novel and general high-dimensional concentration inequalities and Berry-Esseen bounds for vector-valued martingales induced by Markov chains. We apply these results to analyze the performance of the Temporal Difference (TD)…

Machine Learning · Statistics 2026-05-22 Weichen Wu , Yuting Wei , Alessandro Rinaldo

Temporal difference (TD) learning is a popular algorithm for policy evaluation in reinforcement learning, but the vanilla TD can substantially suffer from the inherent optimization variance. A variance reduced TD (VRTD) algorithm was…

Machine Learning · Computer Science 2020-01-13 Tengyu Xu , Zhe Wang , Yi Zhou , Yingbin Liang

In this work, we investigate the generalization properties of random feature methods. Our analysis extends prior results for Tikhonov regularization to a broad class of spectral regularization techniques and further generalizes the setting…

Machine Learning · Statistics 2026-03-03 Mike Nguyen , Nicole Mücke

We develop novel learning rates for conditional mean embeddings by applying the theory of interpolation for reproducing kernel Hilbert spaces (RKHS). We derive explicit, adaptive convergence rates for the sample estimator under the…

Machine Learning · Statistics 2026-04-09 Prem Talwai , Ali Shameli , David Simchi-Levi