English
Related papers

Related papers: Neural Temporal-Difference and Q-Learning Provably…

200 papers

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

We study reinforcement learning under model misspecification, where we do not have access to the true environment but only to a reasonably close approximation to it. We address this problem by extending the framework of robust MDPs to the…

Machine Learning · Computer Science 2017-11-10 Aurko Roy , Huan Xu , Sebastian Pokutta

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

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

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

Machine Learning · Statistics 2025-05-14 Yang Peng , Kaicheng Jin , Liangyu Zhang , Zhihua Zhang

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

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

Our understanding of reinforcement learning (RL) has been shaped by theoretical and empirical results that were obtained decades ago using tabular representations and linear function approximators. These results suggest that RL methods that…

Machine Learning · Computer Science 2018-06-05 Artemij Amiranashvili , Alexey Dosovitskiy , Vladlen Koltun , Thomas Brox

The goal of this paper is to characterize function distributions that deep learning can or cannot learn in poly-time. A universality result is proved for SGD-based deep learning and a non-universality result is proved for GD-based deep…

Machine Learning · Computer Science 2020-01-10 Emmanuel Abbe , Colin Sandon

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

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

Multi-layer feedforward networks have been used to approximate a wide range of nonlinear functions. An important and fundamental problem is to understand the learnability of a network model through its statistical risk, or the expected…

Machine Learning · Computer Science 2022-06-28 Gen Li , Jie Ding

The optimization problem behind neural networks is highly non-convex. Training with stochastic gradient descent and variants requires careful parameter tuning and provides no guarantee to achieve the global optimum. In contrast we show…

Machine Learning · Computer Science 2016-10-31 Antoine Gautier , Quynh Nguyen , Matthias Hein

It is well known that the extension of Watkins' algorithm to general function approximation settings is challenging: does the projected Bellman equation have a solution? If so, is the solution useful in the sense of generating a good…

Optimization and Control · Mathematics 2020-08-11 Prashant G. Mehta , Sean P. Meyn

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

This paper analyzes multi-step temporal difference (TD)-learning algorithms within the ``deadly triad'' scenario, characterized by linear function approximation, off-policy learning, and bootstrapping. In particular, we prove that $n$-step…

Machine Learning · Computer Science 2026-02-24 Han-Dong Lim , Donghwan Lee

Solving a reinforcement learning (RL) problem poses two competing challenges: fitting a potentially discontinuous value function, and generalizing well to new observations. In this paper, we analyze the learning dynamics of temporal…

Machine Learning · Computer Science 2022-06-07 Clare Lyle , Mark Rowland , Will Dabney , Marta Kwiatkowska , Yarin Gal

Regularized Markov Decision Processes serve as models of sequential decision making under uncertainty wherein the decision maker has limited information processing capacity and/or aversion to model ambiguity. With functional approximation,…

Artificial Intelligence · Computer Science 2025-02-11 Jiachen Xi , Alfredo Garcia , Petar Momcilovic

In reinforcement learning, temporal difference-based algorithms can be sample-inefficient: for instance, with sparse rewards, no learning occurs until a reward is observed. This can be remedied by learning richer objects, such as a model of…

Machine Learning · Computer Science 2021-01-19 Léonard Blier , Corentin Tallec , Yann Ollivier

A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the…

Machine Learning · Computer Science 2019-06-12 Difan Zou , Quanquan Gu
‹ Prev 1 3 4 5 6 7 10 Next ›