English
Related papers

Related papers: Stochastic Variance Reduction Methods for Policy E…

200 papers

Stochastic nonconvex-concave min-max saddle point problems appear in many machine learning and control problems including distributionally robust optimization, generative adversarial networks, and adversarial learning. In this paper, we…

Optimization and Control · Mathematics 2023-09-12 Morteza Boroun , Zeinab Alizadeh , Afrooz Jalilzadeh

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications. Previous primal-dual style approaches suffer from instability issues and lack optimality…

Machine Learning · Computer Science 2022-06-20 Zuxin Liu , Zhepeng Cen , Vladislav Isenbaev , Wei Liu , Zhiwei Steven Wu , Bo Li , Ding Zhao

In this paper we propose a class of randomized primal-dual methods to contend with large-scale saddle point problems defined by a convex-concave function $\mathcal{L}(\mathbf{x},y)\triangleq\sum_{i=1}^m f_i(x_i)+\Phi(\mathbf{x},y)-h(y)$. We…

Optimization and Control · Mathematics 2023-03-17 E. Yazdandoost Hamedani , A. Jalilzadeh , N. S. Aybat

In this work, we consider strongly convex strongly concave (SCSC) saddle point (SP) problems $\min_{x\in\mathbb{R}^{d_x}}\max_{y\in\mathbb{R}^{d_y}}f(x,y)$ where $f$ is $L$-smooth, $f(.,y)$ is $\mu$-strongly convex for every $y$, and…

Optimization and Control · Mathematics 2022-02-22 Bugra Can , Mert Gurbuzbalaban , Necdet Serhat Aybat

We study the performance of stochastic first-order methods for finding saddle points of convex-concave functions. A notorious challenge faced by such methods is that the gradients can grow arbitrarily large during optimization, which may…

Machine Learning · Computer Science 2024-06-10 Gergely Neu , Nneka Okolo

Policy gradient algorithms are widely used in reinforcement learning and belong to the class of approximate dynamic programming methods. This paper studies two key policy gradient algorithms, the Natural Policy Gradient and the Gauss-Newton…

Systems and Control · Electrical Eng. & Systems 2026-05-11 Bowen Song , Sebastien Gros , Andrea Iannelli

We study the safe reinforcement learning problem with nonlinear function approximation, where policy optimization is formulated as a constrained optimization problem with both the objective and the constraint being nonconvex functions. For…

Machine Learning · Computer Science 2019-10-29 Ming Yu , Zhuoran Yang , Mladen Kolar , Zhaoran Wang

We consider (stochastic) convex-concave saddle point (SP) problems with high-dimensional decision variables, arising in various applications including machine learning problems. To contend with the challenges in computing full gradients, we…

Optimization and Control · Mathematics 2025-09-30 Erfan Yazdandoost Hamedani , Afrooz Jalilzadeh , Necdet Serhat Aybat

The article is devoted to the development of algorithmic methods ensuring efficient complexity bounds for strongly convex-concave saddle point problems in the case when one of the groups of variables is high-dimensional, and the other is…

Optimization and Control · Mathematics 2022-10-26 Egor Gladin , Ilya Kuruzov , Fedor Stonyakin , Dmitry Pasechnyuk , Mohammad Alkousa , Alexander Gasnikov

The proliferation of saddle points, rather than poor local minima, is increasingly understood to be a primary obstacle in large-scale non-convex optimization for machine learning. Variable elimination algorithms, like Variable Projection…

Machine Learning · Computer Science 2025-11-04 Min Gan , Guang-Yong Chen , Yang Yi , Lin Yang

In recent years, reinforcement learning (RL) systems with general goals beyond a cumulative sum of rewards have gained traction, such as in constrained problems, exploration, and acting upon prior experiences. In this paper, we consider…

Machine Learning · Computer Science 2020-07-07 Junyu Zhang , Alec Koppel , Amrit Singh Bedi , Csaba Szepesvari , Mengdi Wang

Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any improper data-collecting…

Machine Learning · Computer Science 2025-03-21 Shuze Daniel Liu , Claire Chen , Shangtong Zhang

In this paper, we study the gradient descent-ascent method for convex-concave saddle-point problems. We derive a new non-asymptotic global convergence rate in terms of distance to the solution set by using the semidefinite programming…

Optimization and Control · Mathematics 2022-09-19 Moslem Zamani , Hadi Abbaszadehpeivasti , Etienne de Klerk

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

Using convex combination and linesearch techniques, we introduce a novel primal-dual algorithm for solving structured convex-concave saddle point problems with a generic smooth nonbilinear coupling term. Our adaptive linesearch strategy…

Optimization and Control · Mathematics 2024-01-17 Xiaokai Chang , Junfeng Yang , Hongchao Zhang

Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents. Motivated by decentralized applications such as sensor networks, swarm…

Machine Learning · Computer Science 2019-01-10 Hoi-To Wai , Zhuoran Yang , Zhaoran Wang , Mingyi Hong

In reinforcement learning (RL) , one of the key components is policy evaluation, which aims to estimate the value function (i.e., expected long-term accumulated reward) of a policy. With a good policy evaluation method, the RL algorithms…

Machine Learning · Computer Science 2018-09-25 Yue Wang , Wei Chen , Yuting Liu , Zhi-Ming Ma , Tie-Yan Liu

Off-policy learning is key to scaling up reinforcement learning as it allows to learn about a target policy from the experience generated by a different behavior policy. Unfortunately, it has been challenging to combine off-policy learning…

Machine Learning · Computer Science 2019-01-04 Ahmed Touati , Pierre-Luc Bacon , Doina Precup , Pascal Vincent

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

This paper explores numerical methods for solving a convex differentiable semi-infinite program. We introduce a primal-dual gradient method which performs three updates iteratively: a momentum gradient ascend step to update the constraint…

Optimization and Control · Mathematics 2024-07-23 Yao Yao , Qihang Lin , Tianbao Yang