English
Related papers

Related papers: Convergence of off-policy TD(0) with linear functi…

200 papers

Addressing such diverse ends as safety alignment with human preferences, and the efficiency of learning, a growing line of reinforcement learning research focuses on risk functionals that depend on the entire distribution of returns. Recent…

Machine Learning · Computer Science 2022-09-22 Audrey Huang , Liu Leqi , Zachary Chase Lipton , Kamyar Azizzadenesheli

Off-policy prediction -- learning the value function for one policy from data generated while following another policy -- is one of the most challenging subproblems in reinforcement learning. This paper presents empirical results with…

Machine Learning · Computer Science 2021-06-15 Sina Ghiassian , Richard S. Sutton

Many popular policy gradient methods for reinforcement learning follow a biased approximation of the policy gradient known as the discounted approximation. While it has been shown that the discounted approximation of the policy gradient is…

Machine Learning · Computer Science 2023-01-10 Chris Nota

We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks. We analyze the deep fitted Q-evaluation method for estimating the expected cumulative reward of a target policy, when the data…

Machine Learning · Computer Science 2022-10-05 Xiang Ji , Minshuo Chen , Mengdi Wang , Tuo Zhao

This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history…

Machine Learning · Computer Science 2020-02-25 Yaqi Duan , Mengdi Wang

Temporal difference (TD) learning is a fundamental algorithm for estimating value functions in reinforcement learning. Recent finite-time analyses of TD with linear function approximation quantify its theoretical convergence rate. However,…

Machine Learning · Computer Science 2026-03-04 Yunxiang Li , Mark Schmidt , Reza Babanezhad , Sharan Vaswani

We study reinforcement learning methods with linear function approximation under non-Markov state and cost processes. We first consider the policy evaluation method and show that the algorithm converges under suitable ergodicity conditions…

Machine Learning · Computer Science 2026-01-05 Ali Devran Kara

We study offline reinforcement learning problems with a long-run average reward objective. The state-action pairs generated by any fixed behavioral policy thus follow a Markov chain, and the {\em empirical} state-action-next-state…

Optimization and Control · Mathematics 2025-03-18 Mengmeng Li , Daniel Kuhn , Tobias Sutter

Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their objective functions is optimal w.r.t approximating the true…

Machine Learning · Computer Science 2017-04-21 Bo Liu , Daoming Lyu , Wen Dong , Saad Biaz

We study the off-policy evaluation (OPE) problem in reinforcement learning with linear function approximation, which aims to estimate the value function of a target policy based on the offline data collected by a behavior policy. We propose…

Machine Learning · Computer Science 2022-01-05 Yifei Min , Tianhao Wang , Dongruo Zhou , Quanquan Gu

In this paper we propose several novel distributed gradient-based temporal difference algorithms for multi-agent off-policy learning of linear approximation of the value function in Markov decision processes with strict information…

Machine Learning · Computer Science 2021-04-20 Milos S. Stankovic , Marko Beko , Srdjan S. Stankovic

In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The purpose of distributional TD learning is to estimate the return distribution of a…

Machine Learning · Statistics 2025-11-18 Kaicheng Jin , Yang Peng , Jiansheng Yang , Zhihua Zhang

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

We consider emphatic temporal-difference learning algorithms for policy evaluation in discounted Markov decision processes with finite spaces. Such algorithms were recently proposed by Sutton, Mahmood, and White (2015) as an improved…

Machine Learning · Computer Science 2017-12-29 Huizhen Yu

We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the…

Machine Learning · Computer Science 2019-07-09 Yao Liu , Adith Swaminathan , Alekh Agarwal , Emma Brunskill

We consider off-policy policy evaluation with function approximation (FA) in average-reward MDPs, where the goal is to estimate both the reward rate and the differential value function. For this problem, bootstrapping is necessary and,…

Machine Learning · Computer Science 2022-10-19 Shangtong Zhang , Yi Wan , Richard S. Sutton , Shimon Whiteson

The average reward is a fundamental performance metric in reinforcement learning (RL) focusing on the long-run performance of an agent. Differential temporal difference (TD) learning algorithms are a major advance for average reward RL as…

Machine Learning · Computer Science 2026-02-19 Ethan Blaser , Jiuqi Wang , Shangtong Zhang

In this paper, we develop a novel variant of off-policy natural actor-critic algorithm with linear function approximation and we establish a sample complexity of $\mathcal{O}(\epsilon^{-3})$, outperforming all the previously known…

Machine Learning · Computer Science 2022-04-13 Zaiwei Chen , Sajad Khodadadian , Siva Theja Maguluri

Since the objective functions of reinforcement learning problems are typically highly nonconvex, it is desirable that policy gradient, the most popular algorithm, escapes saddle points and arrives at second-order stationary points. Existing…

Machine Learning · Computer Science 2024-05-15 Siqiao Mu , Diego Klabjan

We study the policy evaluation problem in multi-agent reinforcement learning. In this problem, a group of agents works cooperatively to evaluate the value function for the global discounted accumulative reward problem, which is composed of…

Optimization and Control · Mathematics 2019-06-04 Thinh T. Doan , Siva Theja Maguluri , Justin Romberg