English
Related papers

Related papers: A Gauss-Newton Method for Markov Decision Processe…

200 papers

Gradient-based algorithms are one of the methods of choice for the optimisation of Markov Decision Processes. In this article we will present a novel approximate Newton algorithm for the optimisation of such models. The algorithm has…

Optimization and Control · Mathematics 2015-08-05 Thomas Furmston , David Barber

Recently two approximate Newton methods were proposed for the optimisation of Markov Decision Processes. While these methods were shown to have desirable properties, such as a guarantee that the preconditioner is negative-semidefinite when…

Optimization and Control · Mathematics 2015-08-05 Thomas Furmston , Guy Lever

In this paper we present a review of the connections between classical algorithms for solving Markov Decision Processes (MDPs) and classical gradient-based algorithms in convex optimization. Some of these connections date as far back as the…

Optimization and Control · Mathematics 2021-11-29 Julien Grand-Clément

Policy gradient algorithms have been widely applied to Markov decision processes and reinforcement learning problems in recent years. Regularization with various entropy functions is often used to encourage exploration and improve…

Machine Learning · Computer Science 2023-06-09 Haoya Li , Samarth Gupta , Hsiangfu Yu , Lexing Ying , Inderjit Dhillon

In this paper, we propose new proximal Newton-type methods for convex optimization problems in composite form. The applications include model predictive control (MPC) and embedded MPC. Our new methods are computationally attractive since…

Optimization and Control · Mathematics 2020-07-21 Ilan Adler , Zhiyue Tom Hu , Tianyi Lin

Quasi-Newton methods form an important class of methods for solving nonlinear optimization problems. In such methods, first order information is used to approximate the second derivative. The aim is to mimic the fast convergence that can be…

Optimization and Control · Mathematics 2025-02-20 Aban Ansari-Önnestam , Anders Forsgren

Using quasi-Newton methods in stochastic optimization is not a trivial task given the difficulty of extracting curvature information from the noisy gradients. Moreover, pre-conditioning noisy gradient observations tend to amplify the noise.…

Optimization and Control · Mathematics 2024-04-02 Andre Carlon , Luis Espath , Raul Tempone

This paper presents a model-free approximation for the Hessian of the performance of deterministic policies to use in the context of Reinforcement Learning based on Quasi-Newton steps in the policy parameters. We show that the approximate…

Machine Learning · Computer Science 2022-03-29 Arash Bahari Kordabad , Hossein Nejatbakhsh Esfahani , Wenqi Cai , Sebastien Gros

Second-order optimization methods are among the most widely used optimization approaches for convex optimization problems, and have recently been used to optimize non-convex optimization problems such as deep learning models. The widely…

Optimization and Control · Mathematics 2022-02-01 Dinesh Singh , Hardik Tankaria , Makoto Yamada

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

In this paper, We propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems. To model policy functions in MDP, we employ Gaussian mixture model (GMM) and…

Machine Learning · Computer Science 2020-05-20 Shijun Wang , Baocheng Zhu , Chen Li , Mingzhe Wu , James Zhang , Wei Chu , Yuan Qi

Newton's method is the most widespread high-order method, demanding the gradient and the Hessian of the objective function. However, one of the main disadvantages of Newtons method is its lack of global convergence and high iteration cost.…

We present an algorithm for minimizing a sum of functions that combines the computational efficiency of stochastic gradient descent (SGD) with the second order curvature information leveraged by quasi-Newton methods. We unify these…

Machine Learning · Computer Science 2014-12-02 Jascha Sohl-Dickstein , Ben Poole , Surya Ganguli

Optimization problems, arise in many practical applications, from the view points of both theory and numerical methods. Especially, significant improvement in deep learning training came from the Quasi-Newton methods. Quasi-Newton search…

Optimization and Control · Mathematics 2024-11-19 Jiongcheng Li

Recent control algorithms for Markov decision processes (MDPs) have been designed using an implicit analogy with well-established optimization algorithms. In this paper, we adopt the quasi-Newton method (QNM) from convex optimization to…

Optimization and Control · Mathematics 2026-01-06 Mohammad Amin Sharifi Kolarijani , Peyman Mohajerin Esfahani

In recent years, various subspace algorithms have been developed to handle large-scale optimization problems. Although existing subspace Newton methods require fewer iterations to converge in practice, the matrix operations and full…

Optimization and Control · Mathematics 2024-06-05 Taisei Miyaishi , Ryota Nozawa , Pierre-Louis Poirion , Akiko Takeda

This paper discusses algorithms for solving Markov decision processes (MDPs) that have monotone optimal policies. We propose a two-stage alternating convex optimization scheme that can accelerate the search for an optimal policy by…

Systems and Control · Computer Science 2017-04-04 Robert Mattila , Cristian R. Rojas , Vikram Krishnamurthy , Bo Wahlberg

Deep learning algorithms often require solving a highly non-linear and nonconvex unconstrained optimization problem. Methods for solving optimization problems in large-scale machine learning, such as deep learning and deep reinforcement…

Machine Learning · Computer Science 2019-09-06 Jacob Rafati , Roummel F. Marcia

A game theory inspired methodology is proposed for finding a function's saddle points. While explicit descent methods are known to have severe convergence issues, implicit methods are natural in an adversarial setting, as they take the…

Optimization and Control · Mathematics 2019-06-04 Montacer Essid , Esteban Tabak , Giulio Trigila

Newton's Method is widely used to find the solution of complex non-linear simulation problems in Computer Graphics. To guarantee a descent direction, it is common practice to clamp the negative eigenvalues of each element Hessian prior to…

Graphics · Computer Science 2026-05-26 José Antonio Fernández-Fernández , Fabian Löschner , Jan Bender
‹ Prev 1 2 3 10 Next ›