English
Related papers

Related papers: Statistical Inference for Temporal Difference Lear…

200 papers

We extend temporal-difference (TD) learning in order to obtain risk-sensitive, model-free reinforcement learning algorithms. This extension can be regarded as modification of the Rescorla-Wagner rule, where the (sigmoidal) stimulus is taken…

Machine Learning · Computer Science 2021-11-05 Grégoire Delétang , Jordi Grau-Moya , Markus Kunesch , Tim Genewein , Rob Brekelmans , Shane Legg , Pedro A. Ortega

While there are convergence guarantees for temporal difference (TD) learning when using linear function approximators, the situation for nonlinear models is far less understood, and divergent examples are known. Here we take a first step…

Machine Learning · Computer Science 2020-02-12 David Brandfonbrener , Joan Bruna

We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and unified proofs of convergence for a variety of…

Machine Learning · Computer Science 2020-03-30 Philip Amortila , Doina Precup , Prakash Panangaden , Marc G. Bellemare

Temporal difference (TD) learning is a cornerstone of reinforcement learning. In the average-reward setting, standard TD($\lambda$) is highly sensitive to the choice of step-size and thus requires careful tuning to maintain numerical…

Machine Learning · Statistics 2025-10-08 Hwanwoo Kim , Dongkyu Derek Cho , Eric Laber

We study the finite-time convergence of projected linear two-time-scale stochastic approximation with constant step sizes and Polyak--Ruppert averaging. We establish an explicit mean-square error bound, decomposing it into two interpretable…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Yitao Bai , Thinh T. Doan , Justin Romberg

A common optimization tool used in deep reinforcement learning is momentum, which consists in accumulating and discounting past gradients, reapplying them at each iteration. We argue that, unlike in supervised learning, momentum in Temporal…

Machine Learning · Computer Science 2021-06-09 Emmanuel Bengio , Joelle Pineau , Doina Precup

Distributionally robust reinforcement learning (DRRL) focuses on designing policies that achieve good performance under model uncertainties. The goal is to maximize the worst-case long-term discounted reward, where the data for RL comes…

Machine Learning · Computer Science 2026-03-17 Saptarshi Mandal , Yashaswini Murthy , R. Srikant

Many reinforcement learning approaches rely on temporal-difference (TD) learning to learn a critic. However, TD-learning updates can be high variance. Here, we introduce a model-based RL framework, Taylor TD, which reduces this variance in…

Machine Learning · Computer Science 2023-10-19 Michele Garibbo , Maxime Robeyns , Laurence Aitchison

Reinforcement learning (RL) has been successfully used to solve many continuous control tasks. Despite its impressive results however, fundamental questions regarding the sample complexity of RL on continuous problems remain open. We study…

Machine Learning · Computer Science 2017-12-27 Stephen Tu , Benjamin Recht

The temporal-difference methods TD($\lambda$) and Sarsa($\lambda$) form a core part of modern reinforcement learning. Their appeal comes from their good performance, low computational cost, and their simple interpretation, given by their…

Artificial Intelligence · Computer Science 2016-09-09 Harm van Seijen , A. Rupam Mahmood , Patrick M. Pilarski , Marlos C. Machado , Richard S. Sutton

Estimating value functions is a core component of reinforcement learning algorithms. Temporal difference (TD) learning algorithms use bootstrapping, i.e. they update the value function toward a learning target using value estimates at…

Machine Learning · Computer Science 2022-01-07 Anthony GX-Chen , Veronica Chelu , Blake A. Richards , Joelle Pineau

We study the exploration problem with approximate linear action-value functions in episodic reinforcement learning under the notion of low inherent Bellman error, a condition normally employed to show convergence of approximate value…

Machine Learning · Computer Science 2020-06-30 Andrea Zanette , Alessandro Lazaric , Mykel Kochenderfer , Emma Brunskill

We develop a new method of online inference for a vector of parameters estimated by the Polyak-Ruppert averaging procedure of stochastic gradient descent (SGD) algorithms. We leverage insights from time series regression in econometrics and…

Machine Learning · Statistics 2022-08-09 Sokbae Lee , Yuan Liao , Myung Hwan Seo , Youngki Shin

Recent advances in vision-language-action (VLA) models for robotics have highlighted the importance of reliable uncertainty quantification in sequential tasks. However, assessing and improving calibration in such settings remains mostly…

Robotics · Computer Science 2026-04-23 Shelly Francis-Meretzki , Mirco Mutti , Yaniv Romano , Aviv Tamar

We consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several…

Machine Learning · Computer Science 2018-03-30 Huizhen Yu

In this paper, we provide a unified analysis of temporal difference learning algorithms with linear function approximators by exploiting their connections to Markov jump linear systems (MJLS). We tailor the MJLS theory developed in the…

Machine Learning · Computer Science 2019-11-06 Bin Hu , Usman Ahmed Syed

This paper addresses stochastic optimization in a streaming setting with time-dependent and biased gradient estimates. We analyze several first-order methods, including Stochastic Gradient Descent (SGD), mini-batch SGD, and time-varying…

Machine Learning · Computer Science 2023-07-20 Antoine Godichon-Baggioni , Nicklas Werge , Olivier Wintenberger

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 study the problem of computing the value function from a discretely-observed trajectory of a continuous-time diffusion process. We develop a new class of algorithms based on easily implementable numerical schemes that are compatible with…

Machine Learning · Computer Science 2024-07-09 Wenlong Mou , Yuhua Zhu

Temporal distances lie at the heart of many algorithms for planning, control, and reinforcement learning that involve reaching goals, allowing one to estimate the transit time between two states. However, prior attempts to define such…

Machine Learning · Computer Science 2025-03-11 Vivek Myers , Chongyi Zheng , Anca Dragan , Sergey Levine , Benjamin Eysenbach
‹ Prev 1 4 5 6 7 8 10 Next ›