English
Related papers

Related papers: Behavior-Induced Mirror-Prox Temporal-Difference L…

200 papers

Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-difference (TD) learning, is known to suffer form divergence…

Machine Learning · Computer Science 2025-04-21 Han-Dong Lim , Donghwan Lee

Policy Mirror Descent (PMD) is a powerful and theoretically sound methodology for sequential decision-making. However, it is not directly applicable to Reinforcement Learning (RL) due to the inaccessibility of explicit action-value…

Machine Learning · Computer Science 2024-11-01 Pietro Novelli , Marco Pratticò , Massimiliano Pontil , Carlo Ciliberto

We fix a fundamental issue in the stochastic extragradient method by providing a new sampling strategy that is motivated by approximating implicit updates. Since the existing stochastic extragradient algorithm, called Mirror-Prox, of…

Optimization and Control · Mathematics 2021-02-22 Konstantin Mishchenko , Dmitry Kovalev , Egor Shulgin , Peter Richtárik , Yura Malitsky

Space-Time Projection (STP) is introduced as a data-driven forecasting approach for high-dimensional and time-resolved data. The method computes extended space-time proper orthogonal modes from training data spanning a prediction horizon…

Machine Learning · Computer Science 2025-04-01 Oliver T. Schmidt

In multivariate time series (MTS) forecasting, many deep learning based methods have been proposed for modeling dependencies at multiple spatial (inter-variate) or temporal (intra-variate) scales. However, existing methods may fail to model…

Machine Learning · Computer Science 2025-09-03 Binqing Wu , Jianlong Huang , Zongjiang Shang , Ling Chen

This paper revisits the temporal difference (TD) learning algorithm for the policy evaluation tasks in reinforcement learning. Typically, the performance of TD(0) and TD($\lambda$) is very sensitive to the choice of stepsizes. Oftentimes,…

Optimization and Control · Mathematics 2021-10-12 Tao Sun , Han Shen , Tianyi Chen , Dongsheng Li

The analysis of Temporal Difference (TD) learning in the average-reward setting faces notable theoretical difficulties because the Bellman operator is not contractive with respect to any norm. This complicates standard analyses of…

Machine Learning · Computer Science 2026-05-05 Haoxing Tian , Zaiwei Chen , Ioannis Ch. Paschalidis , Alex Olshevsky

We consider the problem of learning the optimal policy for infinite-horizon Markov decision processes (MDPs). For this purpose, some variant of Stochastic Mirror Descent is proposed for convex programming problems with Lipschitz-continuous…

Optimization and Control · Mathematics 2022-03-01 Daniil Tiapkin , Alexander Gasnikov

Sutton, Szepesv\'{a}ri and Maei introduced the first gradient temporal-difference (GTD) learning algorithms compatible with both linear function approximation and off-policy training. The goal of this paper is (a) to propose some variants…

Machine Learning · Computer Science 2024-01-23 Donghwan Lee , Han-Dong Lim , Jihoon Park , Okyong Choi

We study the unconstrained and the minimax saddle point variants of the convex multi-stage stochastic programming problem, where consecutive decisions are coupled through the objective functions, rather than through the constraints. We…

Optimization and Control · Mathematics 2026-03-02 Junhui Zhang , Patrick Jaillet

Policy evaluation is a crucial step in many reinforcement-learning procedures, which estimates a value function that predicts states' long-term value under a given policy. In this paper, we focus on policy evaluation with linear function…

Machine Learning · Computer Science 2017-06-12 Simon S. Du , Jianshu Chen , Lihong Li , Lin Xiao , Dengyong Zhou

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

Multi-step temporal difference (TD) learning is an important approach in reinforcement learning, as it unifies one-step TD learning with Monte Carlo methods in a way where intermediate algorithms can outperform either extreme. They address…

Machine Learning · Computer Science 2018-09-10 Kristopher De Asis , Richard S. Sutton

We address the problem of policy evaluation in discounted Markov decision processes, and provide instance-dependent guarantees on the $\ell_\infty$-error under a generative model. We establish both asymptotic and non-asymptotic versions of…

Machine Learning · Statistics 2020-03-17 Koulik Khamaru , Ashwin Pananjady , Feng Ruan , Martin J. Wainwright , Michael I. Jordan

Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes. Most approaches in this paradigm implement a semi-gradient update to boost the learning speed, which consists of ignoring the…

Machine Learning · Computer Science 2026-05-15 Théo Vincent , Kevin Gerhardt , Yogesh Tripathi , Habib Maraqten , Adam White , Martha White , Jan Peters , Carlo D'Eramo

In reinforcement learning, the TD($\lambda$) algorithm is a fundamental policy evaluation method with an efficient online implementation that is suitable for large-scale problems. One practical drawback of TD($\lambda$) is its sensitivity…

Machine Learning · Statistics 2014-12-23 Aviv Tamar , Panos Toulis , Shie Mannor , Edoardo M. Airoldi

Mirror-prox (MP) is a well-known algorithm to solve variational inequality (VI) problems. VI with a monotone operator covers a large group of settings such as convex minimization, min-max or saddle point problems. To get a convergent…

Machine Learning · Computer Science 2020-11-24 Reza Babanezhad , Simon Lacoste-Julien

The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for a class of multi-agent Markov decision processes (MDPs). The temporal-difference (TD) learning is a reinforcement…

Optimization and Control · Mathematics 2020-04-29 Donghwan Lee , Jianghai Hu

Inverse Dynamics Models (IDMs) map visual observations to low-level action commands, serving as central components for data labeling and policy execution in embodied AI. However, their performance degrades severely under manipulator…

Robotics · Computer Science 2026-04-21 Kerui Li , Zhe Jing , Xiaofeng Wang , Zheng Zhu , Yukun Zhou , Guan Huang , Dongze Li , Qingkai Yang , Huaibo Huang

High-index saddle dynamics (HiSD) is an effective approach for computing saddle points of a prescribed Morse index and constructing solution landscapes for complex nonlinear systems. However, for problems with ill-conditioned Hessians…

Numerical Analysis · Mathematics 2026-05-25 Bingzhang Huang , Hua Su , Lei Zhang , Jin Zhao