English
Related papers

Related papers: Geometry and convergence of natural policy gradien…

200 papers

We consider (stochastic) softmax policy gradient (PG) methods for bandits and tabular Markov decision processes (MDPs). While the PG objective is non-concave, recent research has used the objective's smoothness and gradient domination…

Machine Learning · Computer Science 2024-10-01 Michael Lu , Matin Aghaei , Anant Raj , Sharan Vaswani

This paper studies a policy optimization problem arising from collaborative multi-agent reinforcement learning in a decentralized setting where agents communicate with their neighbors over an undirected graph to maximize the sum of their…

Optimization and Control · Mathematics 2022-09-07 Jinchi Chen , Jie Feng , Weiguo Gao , Ke Wei

Stochastic gradient descent (SGD) is a promising method for solving large-scale inverse problems, due to its excellent scalability with respect to data size. In this work, we analyze a new data-driven regularized stochastic gradient descent…

Numerical Analysis · Mathematics 2024-09-30 Zehui Zhou

Policy Mirror Descent (PMD) is a popular framework in reinforcement learning, serving as a unifying perspective that encompasses numerous algorithms. These algorithms are derived through the selection of a mirror map and enjoy finite-time…

Machine Learning · Statistics 2026-01-07 Carlo Alfano , Sebastian Towers , Silvia Sapora , Chris Lu , Patrick Rebeschini

Trust-region methods have yielded state-of-the-art results in policy search. A common approach is to use KL-divergence to bound the region of trust resulting in a natural gradient policy update. We show that the natural gradient and trust…

Machine Learning · Computer Science 2019-02-11 Joni Pajarinen , Hong Linh Thai , Riad Akrour , Jan Peters , Gerhard Neumann

We analyze the convergence rate of a family of inertial algorithms, which can be obtained by discretization of an inertial system with Hessian-driven damping. We recover a convergence rate, up to a factor of 2 speedup upon Nesterov's…

Optimization and Control · Mathematics 2025-02-25 Zepeng Wang , Juan Peypouquet

The reinforcement learning algorithm SARSA combined with linear function approximation has been shown to converge for infinite horizon discounted Markov decision problems (MDPs). In this paper, we investigate the convergence of the…

Machine Learning · Computer Science 2023-06-08 Lina Palmborg

An appealing property of the natural gradient is that it is invariant to arbitrary differentiable reparameterizations of the model. However, this invariance property requires infinitesimal steps and is lost in practical implementations with…

Machine Learning · Computer Science 2018-06-11 Yang Song , Jiaming Song , Stefano Ermon

In a Hilbert setting, for convex differentiable optimization, we consider accelerated gradient dynamics combining Tikhonov regularization with Hessian-driven damping. The Tikhonov regularization parameter is assumed to tend to zero as time…

Optimization and Control · Mathematics 2022-04-01 Hedy Attouch , Aicha Balhag , Zaki Chbani , Hassan Riahi

Finding Nash equilibria in two-player zero-sum imperfect-information games remains a central challenge in multi-agent reinforcement learning. Recent multi-round regularization methods offer a promising direction, yet existing approaches…

Machine Learning · Computer Science 2026-05-01 Eason Yu , Tzu Hao Liu , Clément L. Canonne , Yunke Wang , Chang Xu , Nguyen H. Tran , Stefano V. Albrecht

In this paper, we propose a first second-order scheme based on arbitrary non-Euclidean norms, incorporated by Bregman distances. They are introduced directly in the Newton iterate with regularization parameter proportional to the square…

Optimization and Control · Mathematics 2021-12-07 Nikita Doikov , Yurii Nesterov

This paper studies stochastic control problems with the action space taken to be probability measures, with the objective penalised by the relative entropy. We identify suitable metric space on which we construct a gradient flow for the…

Optimization and Control · Mathematics 2024-01-26 David Šiška , Łukasz Szpruch

We propose a regularized Hessian-free Newton-type method for minimizing smooth convex functions with Lipschitz continuous Hessians. The algorithm constructs an approximate Hessian by finite differences and selects the regularization…

Optimization and Control · Mathematics 2026-05-01 Leandro Farias Maia , Antonio Victor B. Nascimento , Paulo Sergio M. Santos , Gilson N. Silva

We develop a neural-network framework for multi-period risk--reward stochastic control problems with constrained two-step feedback policies that may be discontinuous in the state. We allow a broad class of objectives built on a…

Computational Finance · Quantitative Finance 2026-03-09 Chang Chen , Duy-Minh Dang

We consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several…

Machine Learning · Computer Science 2018-03-30 Huizhen Yu

Solving partially observable Markov decision processes (POMDPs) remains a fundamental challenge in reinforcement learning (RL), primarily due to the curse of dimensionality induced by the non-stationarity of optimal policies. In this work,…

Optimization and Control · Mathematics 2025-10-20 Semih Cayci , Atilla Eryilmaz

Natural Gradient Descent, a second-degree optimization method motivated by the information geometry, makes use of the Fisher Information Matrix instead of the Hessian which is typically used. However, in many cases, the Fisher Information…

Machine Learning · Computer Science 2023-03-10 Rajesh Shrestha

In this paper, we propose a novel reinforcement- learning algorithm consisting in a stochastic variance-reduced version of policy gradient for solving Markov Decision Processes (MDPs). Stochastic variance-reduced gradient (SVRG) methods…

Machine Learning · Computer Science 2018-06-15 Matteo Papini , Damiano Binaghi , Giuseppe Canonaco , Matteo Pirotta , Marcello Restelli

We study stochastic inexact Newton methods and consider their application in nonconvex settings. Building on the work of [R. Bollapragada, R. H. Byrd, and J. Nocedal, IMA Journal of Numerical Analysis, 39 (2018), pp. 545--578] we derive…

Optimization and Control · Mathematics 2019-08-02 Thomas O'Leary-Roseberry , Nick Alger , Omar Ghattas

This paper is concerned with convergence of stochastic gradient algorithms with momentum terms in the nonconvex setting. A class of stochastic momentum methods, including stochastic gradient descent, heavy ball, and Nesterov's accelerated…

Optimization and Control · Mathematics 2021-10-01 Zixuan Wang , Shanjian Tang