English
Related papers

Related papers: Reducing Sampling Error in Batch Temporal Differen…

200 papers

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

This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes. We investigate the sample complexities required to guarantee a predefined estimation…

Machine Learning · Statistics 2024-05-03 Gen Li , Weichen Wu , Yuejie Chi , Cong Ma , Alessandro Rinaldo , Yuting Wei

The problem of on-line off-policy evaluation (OPE) has been actively studied in the last decade due to its importance both as a stand-alone problem and as a module in a policy improvement scheme. However, most Temporal Difference (TD) based…

Machine Learning · Statistics 2017-02-24 Assaf Hallak , Shie Mannor

Accurate value estimates are important for off-policy reinforcement learning. Algorithms based on temporal difference learning typically are prone to an over- or underestimation bias building up over time. In this paper, we propose a…

Machine Learning · Computer Science 2022-10-24 Nicolai Dorka , Tim Welschehold , Joschka Boedecker , Wolfram Burgard

It is still common to use Q-learning and temporal difference (TD) learning-even though they have divergence issues and sound Gradient TD alternatives exist-because divergence seems rare and they typically perform well. However, recent work…

Machine Learning · Computer Science 2020-09-21 Sina Ghiassian , Andrew Patterson , Shivam Garg , Dhawal Gupta , Adam White , Martha White

In this paper we consider the problem of obtaining sharp bounds for the performance of temporal difference (TD) methods with linear function approximation for policy evaluation in discounted Markov decision processes. We show that a simple…

Machine Learning · Statistics 2024-06-18 Sergey Samsonov , Daniil Tiapkin , Alexey Naumov , Eric Moulines

We initiate the study of federated reinforcement learning under environmental heterogeneity by considering a policy evaluation problem. Our setup involves $N$ agents interacting with environments that share the same state and action space…

Machine Learning · Computer Science 2024-07-02 Han Wang , Aritra Mitra , Hamed Hassani , George J. Pappas , James Anderson

Deep reinforcement learning algorithms that learn policies by trial-and-error must learn from limited amounts of data collected by actively interacting with the environment. While many prior works have shown that proper regularization…

Machine Learning · Computer Science 2023-04-21 Qiyang Li , Aviral Kumar , Ilya Kostrikov , Sergey Levine

Policy evaluation in reinforcement learning is often conducted using two-timescale stochastic approximation, which results in various gradient temporal difference methods such as GTD(0), GTD2, and TDC. Here, we provide convergence rate…

Machine Learning · Computer Science 2019-12-05 Gal Dalal , Balazs Szorenyi , Gugan Thoppe

In the landscape of TD algorithms, the Q($\sigma$, $\lambda$) algorithm is an algorithm with the ability to perform a multistep backup in an online manner while also successfully unifying the concepts of sampling with using the expectation…

Machine Learning · Computer Science 2019-12-24 Abhishek Nan

Temporal-Difference (TD) learning with nonlinear smooth function approximation for policy evaluation has achieved great success in modern reinforcement learning. It is shown that such a problem can be reformulated as a stochastic…

Machine Learning · Computer Science 2020-08-25 Shuang Qiu , Zhuoran Yang , Xiaohan Wei , Jieping Ye , Zhaoran Wang

While off-policy temporal difference (TD) methods have widely been used in reinforcement learning due to their efficiency and simple implementation, their Bayesian counterparts have not been utilized as frequently. One reason is that the…

Machine Learning · Computer Science 2019-10-25 Heejin Jeong , Clark Zhang , George J. Pappas , Daniel D. Lee

An effective approach to exploration in reinforcement learning is to rely on an agent's uncertainty over the optimal policy, which can yield near-optimal exploration strategies in tabular settings. However, in non-tabular settings that…

Predicting missing facts for temporal knowledge graphs (TKGs) is a fundamental task, called temporal knowledge graph completion (TKGC). One key challenge in this task is the imbalance in data distribution, where facts are unevenly spread…

Machine Learning · Computer Science 2025-01-03 Jiasheng Zhang , Deqiang Ouyang , Shuang Liang , Jie Shao

Motivated by the previous success of Two-Dimensional Convolutional Neural Network (2D CNN) on image recognition, researchers endeavor to leverage it to characterize videos. However, one limitation of applying 2D CNN to analyze videos is…

Computer Vision and Pattern Recognition · Computer Science 2020-07-16 Junwu Weng , Donghao Luo , Yabiao Wang , Ying Tai , Chengjie Wang , Jilin Li , Feiyue Huang , Xudong Jiang , Junsong Yuan

Learning a predictive model of the mean return, or value function, plays a critical role in many reinforcement learning algorithms. Distributional reinforcement learning (DRL) has been shown to improve performance by modeling the value…

Machine Learning · Computer Science 2025-07-08 Ju-Seung Byun , Andrew Perrault

Emphatic algorithms are temporal-difference learning algorithms that change their effective state distribution by selectively emphasizing and de-emphasizing their updates on different time steps. Recent works by Sutton, Mahmood and White…

Machine Learning · Computer Science 2015-07-07 A. Rupam Mahmood , Huizhen Yu , Martha White , Richard S. Sutton

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

A hallmark of modern large-scale machine learning techniques is the use of training objectives that provide dense supervision to intermediate computations, such as teacher forcing the next token in language models or denoising step-by-step…

Machine Learning · Computer Science 2025-10-24 Bhavya Agrawalla , Michal Nauman , Khush Agrawal , Aviral Kumar

We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequences of financial transactions. The model is trained using a self-supervised contrastive…

Machine Learning · Computer Science 2026-05-22 Danny Butvinik , Yonit Marcus , Nitzan Tal , Gabrielle Azoulay