paper-with-me

홈 › Papers

Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples

2026-06-04 · Ziad Kobeissi, Éloïse Berthier arxiv

In this paper, we study the finite-time behavior of the TD(0) temporal-difference method with linear function approximation (LFA). We consider on-policy independent and identically distributed (i.i.d.) samples, a constant learning step, and the Polyak-Juditsky averaging method. We establish a new convergence rate, for the Mean-Square Error (MSE) on the approximated function, that is (i) fast in the sense that it admits an optimal dependency in the number of iterations k (i.e., of order 1/k), (ii) robust to ill-conditioning: it only depends on an initial error and modelindependent constants and (iii) sharp up to a multiplicative constant lower than 11. In particular, it does not depend on the smallest eigenvalue of the uncentered covariance matrix of the linear parametrization, unlike all pre-existing O(1/k) rates in the TD(0) literature. We also introduce PCTD(0), a variant of TD(0), which benefits from better convergence properties under an additional assumption of strong mixing on the Markov Chain.

📄 PDF Abstract BibTeX arXiv:2606.05967

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation

2021-06-08 · Semih Cayci, Niao He, R. Srikant

Natural policy gradient (NPG) methods with entropy regularization achieve impressive empirical success in reinforcement learning problems with large state-action spaces. However, their convergence properties and the impa…

Dual Approximation Policy Optimization

2024-10-02 · Zhihan Xiong, Maryam Fazel, Lin Xiao

We propose Dual Approximation Policy Optimization (DAPO), a framework that incorporates general function approximation into policy mirror descent methods. In contrast to the popular approach of using the $L_2$-norm to me…

A new convergent variant of Q-learning with linear function approximation

2020-12-01 · NeurIPS 2020 12 · Diogo Carvalho, Francisco S. Melo, Pedro Santos

In this work, we identify a novel set of conditions that ensure convergence with probability 1 of Q-learning with linear function approximation, by proposing a two time-scale variation thereof. In the faster time scale, …

Q-LearningReinforcement Learning (RL)

Fast Convergence of Softmax Policy Mirror Ascent

2024-11-18 · Reza Asad, Reza Babanezhad, Issam Laradji, Nicolas Le Roux 외

Natural policy gradient (NPG) is a common policy optimization algorithm and can be viewed as mirror ascent in the space of probabilities. Recently, Vaswani et al. [2021] introduced a policy gradient method that correspon…

MuJoCo

Neural Lyapunov Function Approximation with Self-Supervised Reinforcement Learning

2025-03-19 · Luc McCutcheon, Bahman Gharesifard, Saber Fallah

Control Lyapunov functions are traditionally used to design a controller which ensures convergence to a desired state, yet deriving these functions for nonlinear systems remains a complex challenge. This paper presents a…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)