English
Related papers

Related papers: Linear Convergence of Entropy-Regularized Natural …

200 papers

The policy gradient theorem is defined based on an objective with respect to the initial distribution over states. In the discounted case, this results in policies that are optimal for one distribution over initial states, but may not be…

Machine Learning · Computer Science 2019-12-12 Riashat Islam , Raihan Seraj , Pierre-Luc Bacon , Doina Precup

Deep learning achieves remarkable generalization capability with overwhelming number of model parameters. Theoretical understanding of deep learning generalization receives recent attention yet remains not fully explored. This paper…

Machine Learning · Computer Science 2017-11-22 Guanhua Zheng , Jitao Sang , Changsheng Xu

Kakade's natural policy gradient method has been studied extensively in recent years, showing linear convergence with and without regularization. We study another natural gradient method based on the Fisher information matrix of the…

Optimization and Control · Mathematics 2025-02-05 Johannes Müller , Semih Çaycı , Guido Montúfar

State entropy regularization has empirically shown better exploration and sample complexity in reinforcement learning (RL). However, its theoretical guarantees have not been studied. In this paper, we show that state entropy regularization…

Machine Learning · Computer Science 2025-12-02 Yonatan Ashlag , Uri Koren , Mirco Mutti , Esther Derman , Pierre-Luc Bacon , Shie Mannor

Policy gradient (PG) methods are the backbone of many reinforcement learning algorithms due to their good performance in policy optimization problems. As a gradient-based approach, PG methods typically rely on knowledge of the system…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Bowen Song , Andrea Iannelli

We prove the stability and global convergence of a coupled actor-critic gradient flow for infinite-horizon and entropy-regularised Markov decision processes (MDPs) in continuous state and action space with linear function approximation…

Optimization and Control · Mathematics 2025-10-17 Denis Zorba , David Šiška , Lukasz Szpruch

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

Policy gradient methods with actor-critic schemes demonstrate tremendous empirical successes, especially when the actors and critics are parameterized by neural networks. However, it remains less clear whether such "neural" policy gradient…

Machine Learning · Computer Science 2020-06-23 Lingxiao Wang , Qi Cai , Zhuoran Yang , Zhaoran Wang

In this paper, we study the dynamics of temporal difference learning with neural network-based value function approximation over a general state space, namely, \emph{Neural TD learning}. We consider two practically used algorithms,…

Machine Learning · Computer Science 2021-08-09 Semih Cayci , Siddhartha Satpathi , Niao He , R. Srikant

Quadratic assignment problems are a fundamental class of combinatorial optimization problems which are ubiquitous in applications, yet their exact resolution is NP-hard. To circumvent this impasse, it was proposed to regularize such…

Optimization and Control · Mathematics 2025-09-25 Venkatkrishna Karumanchi , Gabriel Rioux , Ziv Goldfeld

Many reinforcement learning algorithms can be seen as versions of approximate policy iteration (API). While standard API often performs poorly, it has been shown that learning can be stabilized by regularizing each policy update by the…

Machine Learning · Computer Science 2021-02-15 Nevena Lazić , Botao Hao , Yasin Abbasi-Yadkori , Dale Schuurmans , Csaba Szepesvári

This paper investigates the computational complexity of reinforcement learning in a novel linear function approximation regime, termed partial $q^{\pi}$-realizability. In this framework, the objective is to learn an $\epsilon$-optimal…

Artificial Intelligence · Computer Science 2025-10-31 Shayan Karimi , Xiaoqi Tan

Maximum entropy (MaxEnt) RL maximizes a combination of the original task reward and an entropy reward. It is believed that the regularization imposed by entropy, on both policy improvement and policy evaluation, together contributes to good…

Machine Learning · Computer Science 2022-02-01 Haonan Yu , Haichao Zhang , Wei Xu

Motivated by applications in reinforcement learning (RL), we study a nonlinear stochastic approximation (SA) algorithm under Markovian noise, and establish its finite-sample convergence bounds under various stepsizes. Specifically, we show…

Optimization and Control · Mathematics 2022-01-27 Zaiwei Chen , Sheng Zhang , Thinh T. Doan , John-Paul Clarke , Siva Theja Maguluri

Temporal-difference learning with gradient correction (TDC) is a two time-scale algorithm for policy evaluation in reinforcement learning. This algorithm was initially proposed with linear function approximation, and was later extended to…

Machine Learning · Computer Science 2021-10-29 Yue Wang , Shaofeng Zou , Yi Zhou

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

Entropy rate of sequential data-streams naturally quantifies the complexity of the generative process. Thus entropy rate fluctuations could be used as a tool to recognize dynamical perturbations in signal sources, and could potentially be…

Information Theory · Computer Science 2014-03-24 Ishanu Chattopadhyay , Hod Lipson

This paper investigates the problem of computing the equilibrium of competitive games, which is often modeled as a constrained saddle-point optimization problem with probability simplex constraints. Despite recent efforts in understanding…

Optimization and Control · Mathematics 2023-01-23 Shicong Cen , Yuting Wei , Yuejie Chi

Natural policy gradient methods are popular reinforcement learning methods that improve the stability of policy gradient methods by utilizing second-order approximations to precondition the gradient with the inverse of the…

Machine Learning · Computer Science 2022-10-12 Brennan Gebotys , Alexander Wong , David A. Clausi

We investigate reinforcement learning in the setting of Markov decision processes for a large number of exchangeable agents interacting in a mean field manner. Applications include, for example, the control of a large number of robots…

Optimization and Control · Mathematics 2025-04-30 René Carmona , Mathieu Laurière , Zongjun Tan