English
Related papers

Related papers: Stochastic Recursive Momentum for Policy Gradient …

200 papers

Reinforcement learning consists of finding policies that maximize an expected cumulative long-term reward in a Markov decision process with unknown transition probabilities and instantaneous rewards. In this paper, we consider the problem…

Systems and Control · Computer Science 2018-07-31 Santiago Paternain , Juan Andrés Bazerque , Austin Small , Alejandro Ribeiro

In this work, we propose a stochastic gradient descent (SGD) framework to design data-driven policy gradient descent algorithms for the linear quadratic regulator problem. Two alternative schemes are considered to estimate the policy…

Systems and Control · Electrical Eng. & Systems 2026-02-24 Bowen Song , Simon Weissmann , Mathias Staudigl , Andrea Iannelli

Risk-sensitive reinforcement learning (RL) has become a popular tool for controlling the risk of uncertain outcomes and ensuring reliable performance in highly stochastic sequential decision-making problems. While it has been shown that…

Machine Learning · Computer Science 2026-01-21 Xian Yu , Lei Ying

This paper presents a novel stochastic gradient descent algorithm for constrained optimization. The proposed algorithm randomly samples constraints and components of the finite sum objective function and relies on a relaxed logarithmic…

Optimization and Control · Mathematics 2025-05-13 Naum Dimitrieski , Jing Cao , Christian Ebenbauer

Decentralized optimization over directed networks is frequently challenged by asymmetric communication and the inherent high variance of stochastic gradients, which collectively cause severe oscillations and hinder algorithmic convergence.…

Optimization and Control · Mathematics 2026-04-10 Wenqi Fan , Yiwei Liao , Qing Xu , Bin Guo , Songyi Dian

We propose the stochastic average gradient (SAG) method for optimizing the sum of a finite number of smooth convex functions. Like stochastic gradient (SG) methods, the SAG method's iteration cost is independent of the number of terms in…

Optimization and Control · Mathematics 2016-05-12 Mark Schmidt , Nicolas Le Roux , Francis Bach

Stochastic compositional optimization arises in many important machine learning tasks such as value function evaluation in reinforcement learning and portfolio management. The objective function is the composition of two expectations of…

Machine Learning · Statistics 2020-01-28 Huizhuo Yuan , Xiangru Lian , Ji Liu

In this work we propose a new primal-dual algorithm with adaptive step-sizes. The stochastic primal-dual hybrid gradient (SPDHG) algorithm with constant step-sizes has become widely applied in large-scale convex optimization across many…

Optimization and Control · Mathematics 2023-12-05 Antonin Chambolle , Claire Delplancke , Matthias J. Ehrhardt , Carola-Bibiane Schönlieb , Junqi Tang

We propose a new stochastic first-order algorithmic framework to solve stochastic composite nonconvex optimization problems that covers both finite-sum and expectation settings. Our algorithms rely on the SARAH estimator introduced in…

Optimization and Control · Mathematics 2019-04-01 Nhan H. Pham , Lam M. Nguyen , Dzung T. Phan , Quoc Tran-Dinh

We propose a stochastic conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms. Existing CGM variants for this template either suffer from slow convergence rates, or…

Machine Learning · Computer Science 2022-04-19 Gideon Dresdner , Maria-Luiza Vladarean , Gunnar Rätsch , Francesco Locatello , Volkan Cevher , Alp Yurtsever

This paper proposes SMADMM, a single-loop Stochastic Momentum Alternating Direction Method of Multipliers for solving a class of nonconvex and nonsmooth composite optimization problems. SMADMM achieves the optimal oracle complexity of…

Optimization and Control · Mathematics 2025-04-22 Kangkang Deng , Shuchang Zhang , Boyu Wang , Jiachen Jin , Juan Zhou , Hongxia Wang

This paper investigates the distributed stochastic nonconvex and nonsmooth composite optimization problem. Existing stochastic typically rely on uniform step size strictly bounded by global network parameters, such as the maximum node…

Optimization and Control · Mathematics 2026-03-10 Yangming Zhang , Yongyang Xiong , Jinming Xu , Keyou You , Yang Shi

The theory of continuous-time reinforcement learning (RL) has progressed rapidly in recent years. While the ultimate objective of RL is typically to learn deterministic control policies, most existing continuous-time RL methods rely on…

Machine Learning · Computer Science 2026-03-17 Ziheng Cheng , Xin Guo , Yufei Zhang

Stochastic variance reduced methods have shown strong performance in solving finite-sum problems. However, these methods usually require the users to manually tune the step-size, which is time-consuming or even infeasible for some…

Optimization and Control · Mathematics 2023-10-10 Binghui Xie , Chenhan Jin , Kaiwen Zhou , James Cheng , Wei Meng

Due to the high variance of policy gradients, on-policy optimization algorithms are plagued with low sample efficiency. In this work, we propose Augment-Reinforce-Merge (ARM) policy gradient estimator as an unbiased low-variance alternative…

Machine Learning · Computer Science 2019-03-14 Yunhao Tang , Mingzhang Yin , Mingyuan Zhou

Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization.…

Machine Learning · Computer Science 2019-11-27 Kaixiang Lin , Jiayu Zhou

In recent years, Riemannian stochastic gradient descent (R-SGD), Riemannian stochastic variance reduction (R-SVRG) and Riemannian stochastic recursive gradient (R-SRG) have attracted considerable attention on Riemannian optimization. Under…

Optimization and Control · Mathematics 2021-10-18 Jiabao Yang

In reinforcement learning, continuous time is often discretized by a time scale $\delta$, to which the resulting performance is known to be highly sensitive. In this work, we seek to find a $\delta$-invariant algorithm for policy gradient…

Machine Learning · Computer Science 2022-01-28 Seohong Park , Jaekyeom Kim , Gunhee Kim

In the paper, we design a novel Bregman gradient policy optimization framework for reinforcement learning based on Bregman divergences and momentum techniques. Specifically, we propose a Bregman gradient policy optimization (BGPO) algorithm…

Machine Learning · Computer Science 2022-03-17 Feihu Huang , Shangqian Gao , Heng Huang

Most methods in reinforcement learning use a Policy Gradient (PG) approach to learn a parametric stochastic policy that maps states to actions. The standard approach is to implement such a mapping via a neural network (NN) whose parameters…

Machine Learning · Computer Science 2024-05-29 Sergio Rozada , Antonio G. Marques
‹ Prev 1 3 4 5 6 7 10 Next ›