English
Related papers

Related papers: Emphatic TD Bellman Operator is a Contraction

200 papers

Gradient temporal difference (Gradient TD) algorithms are a popular class of stochastic approximation (SA) algorithms used for policy evaluation in reinforcement learning. Here, we consider Gradient TD algorithms with an additional heavy…

Machine Learning · Computer Science 2021-11-23 Rohan Deb , Shalabh Bhatnagar

Under non-exponential discounting, we develop a dynamic theory for stopping problems in continuous time. Our framework covers discount functions that induce decreasing impatience. Due to the inherent time inconsistency, we look for…

Optimization and Control · Mathematics 2017-03-13 Yu-Jui Huang , Adrien Nguyen-Huu

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

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

We propose a unified framework to study policy evaluation (PE) and the associated temporal difference (TD) methods for reinforcement learning in continuous time and space. We show that PE is equivalent to maintaining the martingale…

Machine Learning · Computer Science 2022-02-02 Yanwei Jia , Xun Yu Zhou

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Machine Learning · Statistics 2020-02-21 Nathan Kallus , Masatoshi Uehara

Off-policy algorithms, in which a behavior policy differs from the target policy and is used to gain experience for learning, have proven to be of great practical value in reinforcement learning. However, even for simple convex problems…

Machine Learning · Computer Science 2022-09-13 Rong J. B. Zhu , James M. Murray

We quantify the efficiency of temporal difference (TD) learning over the direct, or Monte Carlo (MC), estimator for policy evaluation in reinforcement learning, with an emphasis on estimation of quantities related to rare events. Policy…

Machine Learning · Computer Science 2025-01-17 Xiaoou Cheng , Jonathan Weare

This paper studies the policy mirror descent (PMD) method, which is a general policy optimization framework in reinforcement learning and can cover a wide range of policy gradient methods by specifying difference mirror maps. Existing…

Optimization and Control · Mathematics 2026-01-01 Wenye Li , Hongxu Chen , Jiacai Liu , Ke Wei

The paper [12] examines a concept of equilibrium policies instead of optimal controls in stochastic optimization to analyze a mean-variance portfolio selection problem. We follow the same approach in order to investigate the Merton…

Optimization and Control · Mathematics 2020-04-23 I. Alia , F. Chighoub , N. Khelfallah , J. Vives

Off-policy Actor-Critic algorithms have demonstrated phenomenal experimental performance but still require better explanations. To this end, we show its policy evaluation error on the distribution of transitions decomposes into: a Bellman…

Machine Learning · Computer Science 2021-10-07 Ting-Han Fan , Peter J. Ramadge

Off-policy evaluation (OPE) is a method for estimating the return of a target policy using some pre-collected observational data generated by a potentially different behavior policy. In some cases, there may be unmeasured variables that can…

Machine Learning · Statistics 2023-02-03 Yang Xu , Jin Zhu , Chengchun Shi , Shikai Luo , Rui Song

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

Value function approximation is a crucial module for policy evaluation in reinforcement learning when the state space is large or continuous. The present paper takes a generative perspective on policy evaluation via temporal-difference (TD)…

Machine Learning · Statistics 2021-12-03 Qin Lu , Georgios B. Giannakis

We analyse quantile temporal-difference learning (QTD), a distributional reinforcement learning algorithm that has proven to be a key component in several successful large-scale applications of reinforcement learning. Despite these…

Temporal difference (TD) learning algorithms with neural network function parameterization have well-established empirical success in many practical large-scale reinforcement learning tasks. However, theoretical understanding of these…

Machine Learning · Computer Science 2024-05-08 Zhifa Ke , Zaiwen Wen , Junyu Zhang

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,…

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

We investigate model-based reinforcement learning in contextual Markov decision processes (C-MDPs) in which the context is unobserved and induces confounding in the offline dataset. In such settings, conventional model-learning methods are…

Machine Learning · Computer Science 2025-12-09 Nishanth Venkatesh , Andreas A. Malikopoulos

The empirical mode decomposition (EMD) method and its variants have been extensively employed in the load and renewable forecasting literature. Using this multiresolution decomposition, time series (TS) related to the historical load and…

Systems and Control · Electrical Eng. & Systems 2020-11-24 Nima Safari , George Price , Chi Yung Chung