English
Related papers

Related papers: Temporal-difference learning with nonlinear functi…

200 papers

In a series of recent theoretical works, it was shown that strongly over-parameterized neural networks trained with gradient-based methods could converge exponentially fast to zero training loss, with their parameters hardly varying. In…

Optimization and Control · Mathematics 2020-01-08 Lenaic Chizat , Edouard Oyallon , Francis Bach

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

Temporal Difference (TD) algorithms are widely used in Deep Reinforcement Learning (RL). Their performance is heavily influenced by the size of the neural network. While in supervised learning, the regime of over-parameterization and its…

Machine Learning · Computer Science 2024-02-20 David Brellmann , Eloïse Berthier , David Filliat , Goran Frehse

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

Neural Temporal Difference (TD) Learning is an approximate temporal difference method for policy evaluation that uses a neural network for function approximation. Analysis of Neural TD Learning has proven to be challenging. In this paper we…

Machine Learning · Computer Science 2023-12-12 Haoxing Tian , Ioannis Ch. Paschalidis , Alex Olshevsky

Temporal difference (TD) learning is a foundational algorithm in reinforcement learning (RL). For nearly forty years, TD learning has served as a workhorse for applied RL as well as a building block for more complex and specialized…

Machine Learning · Computer Science 2025-06-24 Hwanwoo Kim , Panos Toulis , Eric Laber

In the training of over-parameterized model functions via gradient descent, sometimes the parameters do not change significantly and remain close to their initial values. This phenomenon is called lazy training, and motivates consideration…

Quantum Physics · Physics 2023-05-03 Erfan Abedi , Salman Beigi , Leila Taghavi

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

While there are convergence guarantees for temporal difference (TD) learning when using linear function approximators, the situation for nonlinear models is far less understood, and divergent examples are known. Here we take a first step…

Machine Learning · Computer Science 2020-02-12 David Brandfonbrener , Joan Bruna

We investigate the finite-time convergence properties of Temporal Difference (TD) learning with linear function approximation, a cornerstone algorithm in the field of reinforcement learning. We are interested in the so-called ``robust''…

Machine Learning · Computer Science 2025-09-26 Wei-Cheng Lee , Francesco Orabona

Despite deep neural networks' powerful representation learning capabilities, theoretical understanding of how networks can simultaneously achieve meaningful feature learning and global convergence remains elusive. Existing approaches like…

Machine Learning · Computer Science 2025-07-23 Zixiang Chen , Greg Yang , Qingyue Zhao , Quanquan Gu

The analysis of Temporal Difference (TD) learning in the average-reward setting faces notable theoretical difficulties because the Bellman operator is not contractive with respect to any norm. This complicates standard analyses of…

Machine Learning · Computer Science 2026-05-05 Haoxing Tian , Zaiwei Chen , Ioannis Ch. Paschalidis , Alex Olshevsky

The goal of this manuscript is to conduct a controltheoretic analysis of Temporal Difference (TD) learning algorithms. TD-learning serves as a cornerstone in the realm of reinforcement learning, offering a methodology for approximating the…

Artificial Intelligence · Computer Science 2023-09-12 Donghwan Lee , Do Wan Kim

Reward models in RLHF are trained to score only the final token of a response - a choice that discards rich signal from every intermediate position and produces models whose token-level outputs are noise. We argue this is a missed…

Machine Learning · Computer Science 2026-04-28 Alex Nikulkov

Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coupling leads to…

Machine Learning · Computer Science 2020-04-16 Qi Cai , Zhuoran Yang , Jason D. Lee , Zhaoran Wang

We address the problem of policy evaluation in discounted Markov decision processes, and provide instance-dependent guarantees on the $\ell_\infty$-error under a generative model. We establish both asymptotic and non-asymptotic versions of…

Machine Learning · Statistics 2020-03-17 Koulik Khamaru , Ashwin Pananjady , Feng Ruan , Martin J. Wainwright , Michael I. Jordan

Reward models are central to both reinforcement learning (RL) with language models and inference-time verification. However, existing reward models often lack temporal consistency, leading to ineffective policy updates and unstable RL…

Machine Learning · Computer Science 2025-09-30 Dan Zhang , Min Cai , Jonathan Light , Ziniu Hu , Yisong Yue , Jie Tang

Motivated by applications in risk-sensitive reinforcement learning, we study mean-variance optimization in a discounted reward Markov Decision Process (MDP). Specifically, we analyze a Temporal Difference (TD) learning algorithm with linear…

Machine Learning · Computer Science 2025-03-13 Tejaram Sangadi , L. A. Prashanth , Krishna Jagannathan

Distributionally robust reinforcement learning (DRRL) focuses on designing policies that achieve good performance under model uncertainties. The goal is to maximize the worst-case long-term discounted reward, where the data for RL comes…

Machine Learning · Computer Science 2026-03-17 Saptarshi Mandal , Yashaswini Murthy , R. Srikant

We study non-parametric estimation of the value function of an infinite-horizon $\gamma$-discounted Markov reward process (MRP) using observations from a single trajectory. We provide non-asymptotic guarantees for a general family of…

Machine Learning · Statistics 2022-11-09 Yaqi Duan , Martin J. Wainwright