English
Related papers

Related papers: Derivative-Free Methods for Policy Optimization: G…

200 papers

Finding the global minimum of non-convex functions is one of the main and most difficult problems in modern optimization. In the first part of the paper, we consider a certain class of "good" non-convex functions that can be bounded above…

Optimization and Control · Mathematics 2022-05-17 Aleksandra Bazarova , Aleksandr Beznosikov , Alexander Gasnikov

We revisit the one-point feedback zeroth-order (ZO) optimization problem, a classical setting in derivative-free optimization where only a single noisy function evaluation is available per query. Compared to their two-point counterparts,…

Optimization and Control · Mathematics 2025-08-19 Haishan Ye , Xiangyu Chang

We develop an approach for solving time-consistent risk-sensitive stochastic optimization problems using model-free reinforcement learning (RL). Specifically, we assume agents assess the risk of a sequence of random variables using dynamic…

Machine Learning · Computer Science 2022-12-01 Anthony Coache , Sebastian Jaimungal

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

The main challenge for adaptive regulation of linear-quadratic systems is the trade-off between identification and control. An adaptive policy needs to address both the estimation of unknown dynamics parameters (exploration), as well as the…

Systems and Control · Computer Science 2019-04-01 Mohamad Kazem Shirani Faradonbeh , Ambuj Tewari , George Michailidis

In this paper, we study the contextual dynamic pricing problem where the market value of a product is linear in its observed features plus some market noise. Products are sold one at a time, and only a binary response indicating success or…

Machine Learning · Computer Science 2022-05-05 Jianqing Fan , Yongyi Guo , Mengxin Yu

The objective function of a matrix factorization model usually aims to minimize the average of a regression error contributed by each element. However, given the existence of stochastic noises, the implicit deviations of sample data from…

Machine Learning · Computer Science 2016-10-31 Guang-He Lee , Shao-Wen Yang , Shou-De Lin

We consider the classic stochastic linear quadratic regulator (LQR) problem under an infinite horizon average stage cost. By leveraging recent policy gradient methods from reinforcement learning, we obtain a first-order method that finds a…

Optimization and Control · Mathematics 2025-02-21 Caleb Ju , Georgios Kotsalis , Guanghui Lan

Model-free reinforcement learning algorithms, such as Q-learning, perform poorly in the early stages of learning in noisy environments, because much effort is spent unlearning biased estimates of the state-action value function. The bias…

Machine Learning · Computer Science 2018-02-01 Roy Fox , Ari Pakman , Naftali Tishby

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

This paper studies an infinite horizon optimal control problem for discrete-time linear system and quadratic criteria, both with random parameters which are independent and identically distributed with respect to time. In this general…

Optimization and Control · Mathematics 2024-03-04 Deyue Li

This paper develops and analyzes a stochastic derivative-free optimization strategy. A key feature is the state-dependent adaptive variance. We prove global convergence in probability with algebraic rate and give the quantitative results in…

Optimization and Control · Mathematics 2023-02-10 Björn Engquist , Kui Ren , Yunan Yang

We study the problem of distributed zero-order optimization for a class of strongly convex functions. They are formed by the average of local objectives, associated to different nodes in a prescribed network of connections. We propose a…

Optimization and Control · Mathematics 2021-06-29 Arya Akhavan , Massimiliano Pontil , Alexandre B. Tsybakov

We consider the problem of minimizing a convex function that is evolving according to unknown and possibly stochastic dynamics, which may depend jointly on time and on the decision variable itself. Such problems abound in the machine…

Optimization and Control · Mathematics 2023-05-30 Joshua Cutler , Dmitriy Drusvyatskiy , Zaid Harchaoui

Derivative-free optimization algorithms are particularly useful for tackling blackbox optimization problems where the objective function arises from complex and expensive procedures that preclude the use of classical gradient-based methods.…

Optimization and Control · Mathematics 2026-03-31 El Houcine Bergou , Youssef Diouane , Vyacheslav Kungurtsev , Clément W. Royer

In this paper, we analyze the optimization landscape of gradient descent methods for static output feedback (SOF) control of discrete-time linear time-invariant systems with quadratic cost. The SOF setting can be quite common, for example,…

Optimization and Control · Mathematics 2023-10-31 Jingliang Duan , Jie Li , Shengbo Eben Li , Lin Zhao

Inverse problems are key issues in several scientific areas, including signal processing and medical imaging. Data-driven approaches for inverse problems aim for learning model and regularization parameters from observed data samples, and…

Optimization and Control · Mathematics 2024-11-28 Mathias Staudigl , Simon Weissmann , Tristan van Leeuwen

Optimal control of stochastic nonlinear dynamical systems is a major challenge in the domain of robot learning. Given the intractability of the global control problem, state-of-the-art algorithms focus on approximate sequential optimization…

Machine Learning · Computer Science 2020-04-23 Joe Watson , Hany Abdulsamad , Jan Peters

In this note we consider the problem of synthesizing optimal control policies for a system from noisy datasets. We present a novel algorithm that takes as input the available dataset and, based on these inputs, computes an optimal policy…

Optimization and Control · Mathematics 2020-03-02 Davide Gagliardi , Giovanni Russo

Zeroth-order (ZO) optimization with ordinal feedback has emerged as a fundamental problem in modern machine learning systems, particularly in human-in-the-loop settings such as reinforcement learning from human feedback, preference…

Optimization and Control · Mathematics 2025-12-23 Haishan Ye