English
Related papers

Related papers: Second-Order Policy Gradient Methods for the Linea…

200 papers

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 propose an inexact variable-metric proximal point algorithm to accelerate gradient-based optimization algorithms. The proposed scheme, called QNing can be notably applied to incremental first-order methods such as the stochastic…

Machine Learning · Statistics 2019-01-30 Hongzhou Lin , Julien Mairal , Zaid Harchaoui

Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper provides a new theoretical interpretation and justification…

Machine Learning · Computer Science 2023-10-24 Adrien Bolland , Gilles Louppe , Damien Ernst

Policy gradient methods are among the most effective methods for large-scale reinforcement learning, and their empirical success has prompted several works that develop the foundation of their global convergence theory. However, prior works…

Machine Learning · Computer Science 2020-12-25 Junzi Zhang , Jongho Kim , Brendan O'Donoghue , Stephen Boyd

We present a new accelerated stochastic second-order method that is robust to both gradient and Hessian inexactness, which occurs typically in machine learning. We establish theoretical lower bounds and prove that our algorithm achieves…

Optimization and Control · Mathematics 2024-05-28 Artem Agafonov , Dmitry Kamzolov , Alexander Gasnikov , Ali Kavis , Kimon Antonakopoulos , Volkan Cevher , Martin Takáč

We consider the problem of scheduling in constrained queueing networks with a view to minimizing packet delay. Modern communication systems are becoming increasingly complex, and are required to handle multiple types of traffic with widely…

Machine Learning · Computer Science 2021-05-04 Mohammani Zaki , Avi Mohan , Aditya Gopalan , Shie Mannor

Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard RL. At the…

Optimization and Control · Mathematics 2023-03-27 Zifan Wang , Yulong Gao , Siyi Wang , Michael M. Zavlanos , Alessandro Abate , Karl H. Johansson

Stochastic control with both inherent random system noise and lack of knowledge on system parameters constitutes the core and fundamental topic in reinforcement learning (RL), especially under non-episodic situations where online learning…

Systems and Control · Electrical Eng. & Systems 2019-06-24 Xin Huang , Duan Li , Daniel Zhuoyu Long

Reinforcement learning (RL) aims to estimate the action to take given a (time-varying) state, with the goal of maximizing a cumulative reward function. Predominantly, there are two families of algorithms to solve RL problems: value-based…

Machine Learning · Computer Science 2025-01-10 Sergio Rozada , Hoi-To Wai , Antonio G. Marques

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

Research into optimisation for deep learning is characterised by a tension between the computational efficiency of first-order, gradient-based methods (such as SGD and Adam) and the theoretical efficiency of second-order, curvature-based…

Machine Learning · Computer Science 2024-06-17 Ross M. Clarke , José Miguel Hernández-Lobato

Training in supervised deep learning is computationally demanding, and the convergence behavior is usually not fully understood. We introduce and study a second-order stochastic quasi-Gauss-Newton (SQGN) optimization method that combines…

Machine Learning · Computer Science 2020-07-02 Christopher Thiele , Mauricio Araya-Polo , Detlef Hohl

We propose and analyse a new methodology based on linear-quadratic regulation (LQR) for stabilising falling liquid films via blowing and suction at the base. LQR methods enable rapidly responding feedback control by precomputing a gain…

Optimization and Control · Mathematics 2023-07-11 Oscar A. Holroyd , Radu Cimpeanu , Susana N. Gomes

Estimating a policy that maps states to actions is a central problem in reinforcement learning. Traditionally, policies are inferred from the so called value functions (VFs), but exact VF computation suffers from the curse of…

Machine Learning · Computer Science 2024-05-29 Sergio Rozada , Antonio G. Marques

We consider the static output feedback control for Linear Quadratic Regulator problems with structured constraints under the assumption that system parameters are unknown. To solve the problem in the model free setting, we propose the…

Optimization and Control · Mathematics 2023-03-21 Shokichi Takakura , Kazuhiro Sato

For various typical cases and situations where the formulation results in an optimal control problem, the Linear Quadratic Regulator (LQR) approach and its variants continue to be highly attractive. In certain scenarios, it can happen that…

Optimization and Control · Mathematics 2023-02-14 Jun Ma , Zilong Cheng , Xiaocong Li , Wenxin Wang , Masayoshi Tomizuka , Tong Heng Lee

In this paper, we present a methodology to deploy the deterministic policy gradient method, using actor-critic techniques, when the optimal policy is approximated using a parametric optimization problem, where safety is enforced via hard…

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

Reinforcement Learning, particularly through policy gradient methods, has played a central role in enabling reasoning capabilities of Large Language Models. However, the optimization stability of policy gradients in this setting remains…

Machine Learning · Computer Science 2026-03-03 Luckeciano C. Melo , Alessandro Abate , Yarin Gal

Second-order methods for neural network optimization have several advantages over methods based on first-order gradient descent, including better scaling to large mini-batch sizes and fewer updates needed for convergence. But they are…

Machine Learning · Computer Science 2017-12-21 Huishuai Zhang , Caiming Xiong , James Bradbury , Richard Socher

Linear-quadratic regulator (LQR) is a landmark problem in the field of optimal control, which is the concern of this paper. Generally, LQR is classified into state-feedback LQR (SLQR) and output-feedback LQR (OLQR) based on whether the full…

Optimization and Control · Mathematics 2024-04-16 Lechen Feng , Yuan-Hua Ni
‹ Prev 1 8 9 10 Next ›