English
Related papers

Related papers: Quasi-Newton Iteration in Deterministic Policy Gra…

200 papers

With the increase of machine learning usage by industries and scientific communities in a variety of tasks such as text mining, image recognition and self-driving cars, automatic setting of hyper-parameter in learning algorithms is a key…

Artificial Intelligence · Computer Science 2018-05-15 Juan Cruz Barsce , Jorge A. Palombarini , Ernesto C. Martínez

In this work, we investigate stochastic quasi-Newton methods for minimizing a finite sum of cost functions over a decentralized network. In Part I, we develop a general algorithmic framework that incorporates stochastic quasi-Newton…

Optimization and Control · Mathematics 2023-03-22 Jiaojiao Zhang , Huikang Liu , Anthony Man-Cho So , Qing Ling

We consider the problem of control in the setting of reinforcement learning (RL), where model information is not available. Policy gradient algorithms are a popular solution approach for this problem and are usually shown to converge to a…

Machine Learning · Computer Science 2023-04-24 Mizhaan Prajit Maniyar , Akash Mondal , Prashanth L. A. , Shalabh Bhatnagar

Traditional policy gradient methods are fundamentally flawed. Natural gradients converge quicker and better, forming the foundation of contemporary Reinforcement Learning such as Trust Region Policy Optimization (TRPO) and Proximal Policy…

Machine Learning · Computer Science 2022-09-07 W. J. A. van Heeswijk

Natural gradients have long been studied in deep reinforcement learning due to their fast convergence properties and covariant weight updates. However, computing natural gradients requires inversion of the Fisher Information Matrix (FIM) at…

Machine Learning · Computer Science 2026-02-12 Yingxiao Huo , Satya Prakash Dash , Radu Stoican , Samuel Kaski , Mingfei Sun

Since its introduction a decade ago, \emph{relative entropy policy search} (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains, not to mention providing algorithmic components used by…

Machine Learning · Computer Science 2021-03-18 Aldo Pacchiano , Jonathan Lee , Peter Bartlett , Ofir Nachum

We present a hybrid algorithm between an evolution strategy and a quasi Newton method. The design is based on the Hessian Estimation Evolution Strategy, which iteratively estimates the inverse square root of the Hessian matrix of the…

Optimization and Control · Mathematics 2025-05-19 Tobias Glasmachers

Reinforcement learning considers the problem of finding policies that maximize an expected cumulative reward in a Markov decision process with unknown transition probabilities. In this paper we consider the problem of finding optimal…

Machine Learning · Computer Science 2020-10-19 Santiago Paternain , Juan Andres Bazerque , Alejandro Ribeiro

We consider infinite-horizon discounted Markov decision processes and study the convergence rates of the natural policy gradient (NPG) and the Q-NPG methods with the log-linear policy class. Using the compatible function approximation…

Machine Learning · Computer Science 2023-02-22 Rui Yuan , Simon S. Du , Robert M. Gower , Alessandro Lazaric , Lin Xiao

Off-policy stochastic actor-critic methods rely on approximating the stochastic policy gradient in order to derive an optimal policy. One may also derive the optimal policy by approximating the action-value gradient. The use of action-value…

Machine Learning · Statistics 2017-03-14 Yemi Okesanjo , Victor Kofia

We consider stochastic zero-order optimization problems, which arise in settings from simulation optimization to reinforcement learning. We propose an adaptive sampling quasi-Newton method where we estimate the gradients of a stochastic…

Optimization and Control · Mathematics 2019-10-31 Raghu Bollapragada , Stefan M. Wild

In this paper, we study structured quasi-Newton methods for optimization problems with orthogonality constraints. Note that the Riemannian Hessian of the objective function requires both the Euclidean Hessian and the Euclidean gradient. In…

Optimization and Control · Mathematics 2018-09-05 Jiang Hu , Bo Jiang , Lin Lin , Zaiwen Wen , Yaxiang Yuan

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently…

Machine Learning · Computer Science 2019-05-15 Andreas Doerr , Michael Volpp , Marc Toussaint , Sebastian Trimpe , Christian Daniel

The paper studies the solution of stochastic optimization problems in which approximations to the gradient and Hessian are obtained through subsampling. We first consider Newton-like methods that employ these approximations and discuss how…

Optimization and Control · Mathematics 2016-09-28 Raghu Bollapragada , Richard Byrd , Jorge Nocedal

Policy gradient methods in reinforcement learning have become increasingly prevalent for state-of-the-art performance in continuous control tasks. Novel methods typically benchmark against a few key algorithms such as deep deterministic…

Machine Learning · Computer Science 2017-08-15 Riashat Islam , Peter Henderson , Maziar Gomrokchi , Doina Precup

Cooperative multi-agent reinforcement learning is a decentralized paradigm in sequential decision making where agents distributed over a network iteratively collaborate with neighbors to maximize global (network-wide) notions of rewards.…

Machine Learning · Computer Science 2021-09-27 Carlo Alfano , Patrick Rebeschini

Accelerating the convergence of second-order optimization, particularly Newton-type methods, remains a pivotal challenge in algorithmic research. In this paper, we extend previous work on the \textbf{Quadratic Gradient (QG)} and rigorously…

Optimization and Control · Mathematics 2026-04-01 John Chiang

Reinforcement Learning (RL) algorithms allow artificial agents to improve their action selections so as to increase rewarding experiences in their environments. Deep Reinforcement Learning algorithms require solving a nonconvex and…

Machine Learning · Computer Science 2019-04-18 Jacob Rafati , Roummel F. Marcia

We devise a control-theoretic reinforcement learning approach to support direct learning of the optimal policy. We establish various theoretical properties of our approach, such as convergence and optimality of our analog of the Bellman…

Machine Learning · Computer Science 2026-04-01 Weiqin Chen , Mark S. Squillante , Chai Wah Wu , Santiago Paternain

We present a methodology to deploy the stochastic policy gradient method, using actor-critic techniques, when the optimal policy is approximated using a parametric optimization problem, allowing one to enforce safety via hard constraints.…

Systems and Control · Electrical Eng. & Systems 2024-09-23 Sebastien Gros , Mario Zanon