English
Related papers

Related papers: Emphatic TD Bellman Operator is a Contraction

200 papers

In this paper we extend temporal difference policy evaluation algorithms to performance criteria that include the variance of the cumulative reward. Such criteria are useful for risk management, and are important in domains such as finance…

Machine Learning · Computer Science 2013-10-15 Aviv Tamar , Dotan Di Castro , Shie Mannor

Motivated by uncertain parameters encountered in Markov decision processes (MDPs), we study the effect of parameter uncertainty on Bellman operator-based methods. Specifically, we consider a family of MDPs where the cost parameters are from…

Optimization and Control · Mathematics 2020-03-03 Sarah H. Q. Li , Assalé Adjé , Pierre-Loïc Garoche , Behçet Açıkmeşe

We address the online unconstrained submodular maximization problem (Online USM), in a setting with stochastic bandit feedback. In this framework, a decision-maker receives noisy rewards from a non monotone submodular function taking values…

Machine Learning · Computer Science 2025-02-13 Julien Zhou , Pierre Gaillard , Thibaud Rahier , Julyan Arbel

Off-policy evaluation (OPE) is the task of estimating the expected reward of a given policy based on offline data previously collected under different policies. Therefore, OPE is a key step in applying reinforcement learning to real-world…

Machine Learning · Computer Science 2021-03-11 Yihao Feng , Ziyang Tang , Na Zhang , Qiang Liu

This paper investigates discrete-time Markov decision processes with recursive utilities (or payoffs) defined by the classic CES aggregator and the Kreps-Porteus certainty equivalent operator. According to the classification introduced by…

Optimization and Control · Mathematics 2025-07-11 Anna Jaśkiewicz , Andrzej S. Nowak

The Koopman operator and its data-driven approximations, such as extended dynamic mode decomposition (EDMD), are widely used for analysing, modelling, and controlling nonlinear dynamical systems. However, when the true Koopman…

Dynamical Systems · Mathematics 2026-02-05 Roland Schurig , Pieter van Goor , Karl Worthmann , Rolf Findeisen

This paper presents four different ways of looking at the well-known Least Squares Temporal Differences (LSTD) algorithm for computing the value function of a Markov Reward Process, each of them leading to different insights: the…

Machine Learning · Statistics 2015-04-06 Kamil Ciosek

Sample efficiency is crucial for imitation learning methods to be applicable in real-world applications. Many studies improve sample efficiency by extending adversarial imitation to be off-policy regardless of the fact that these off-policy…

Machine Learning · Computer Science 2022-04-14 Mingfei Sun , Sam Devlin , Katja Hofmann , Shimon Whiteson

Entropic Dynamics (ED) is a framework for constructing dynamical theories of inference using the tools of inductive reasoning. A central feature of the ED framework is the special focus placed on time. In previous work a global entropic…

General Relativity and Quantum Cosmology · Physics 2018-03-19 Selman Ipek , Mohammad Abedi , Ariel Caticha

Off-policy learning enables a reinforcement learning (RL) agent to reason counterfactually about policies that are not executed and is one of the most important ideas in RL. It, however, can lead to instability when combined with function…

Machine Learning · Computer Science 2025-03-03 Xiaochi Qian , Shangtong Zhang

In this paper, we study the Temporal Difference (TD) learning with linear value function approximation. It is well known that most TD learning algorithms are unstable with linear function approximation and off-policy learning. Recent…

Artificial Intelligence · Computer Science 2016-10-06 Dominik Meyer , Hao Shen , Klaus Diepold

This paper addresses the issue of policy evaluation in Markov Decision Processes, using linear function approximation. It provides a unified view of algorithms such as TD(lambda), LSTD(lambda), iLSTD, residual-gradient TD. It is asserted…

Machine Learning · Computer Science 2007-05-23 Manuel Loth , Philippe Preux

Dynamic Mode Decomposition (DMD) is a data-driven technique to identify a low dimensional linear time invariant dynamics underlying high-dimensional data. For systems in which such underlying low-dimensional dynamics is time-varying, a…

Signal Processing · Electrical Eng. & Systems 2020-04-09 Mustaffa Alfatlawi , Vaibhav Srivastava

We study the finite-time behaviour of the popular temporal difference (TD) learning algorithm when combined with tail-averaging. We derive finite time bounds on the parameter error of the tail-averaged TD iterate under a step-size choice…

Machine Learning · Computer Science 2024-09-20 Gandharv Patil , Prashanth L. A. , Dheeraj Nagaraj , Doina Precup

We study the evolution of distributions under the action of an ergodic dynamical system, which may be stochastic in nature. By employing tools from Koopman and transfer operator theory one can evolve any initial distribution of the state…

Machine Learning · Statistics 2023-12-22 Prune Inzerilli , Vladimir Kostic , Karim Lounici , Pietro Novelli , Massimiliano Pontil

Temporal difference (TD) methods constitute a class of methods for learning predictions in multi-step prediction problems, parameterized by a recency factor lambda. Currently the most important application of these methods is to temporal…

Artificial Intelligence · Computer Science 2008-02-03 P. Cichosz

Policy iteration and value iteration are at the core of many (approximate) dynamic programming methods. For Markov Decision Processes with finite state and action spaces, we show that they are instances of semismooth Newton-type methods to…

Optimization and Control · Mathematics 2022-06-28 Matilde Gargiani , Andrea Zanelli , Dominic Liao-McPherson , Tyler Summers , John Lygeros

Off-policy sampling and experience replay are key for improving sample efficiency and scaling model-free temporal difference learning methods. When combined with function approximation, such as neural networks, this combination is known as…

Machine Learning · Computer Science 2021-07-13 Ray Jiang , Shangtong Zhang , Veronica Chelu , Adam White , Hado van Hasselt

Gradient temporal-difference (GTD) learning algorithms are widely used for off-policy policy evaluation with function approximation. However, existing convergence analyses rely on the restrictive assumption that the so-called feature…

Machine Learning · Computer Science 2026-05-11 Hyunjun Na , Donghwan Lee

Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces…

Machine Learning · Computer Science 2026-05-26 Changyu Chen , Xiting Wang , Rui Yan
‹ Prev 1 4 5 6 7 8 10 Next ›