English
Related papers

Related papers: Stochastic Recursive Momentum for Policy Gradient …

200 papers

Stochastic variance reduced gradient (SVRG) is a popular variance reduction technique for accelerating stochastic gradient descent (SGD). We provide a first analysis of the method for solving a class of linear inverse problems in the lens…

Numerical Analysis · Mathematics 2022-01-19 Bangti Jin , Zehui Zhou , Jun Zou

In this paper, we propose a new policy iteration algorithm to compute the value function and the optimal controls of continuous time stochastic control problems. The algorithm relies on successive approximations using linear-quadratic…

Optimization and Control · Mathematics 2024-09-09 Dylan Possamaï , Ludovic Tangpi

We study policy gradient methods for continuous-action, entropy-regularized reinforcement learning through the lens of Wasserstein geometry. Starting from a Wasserstein proximal update, we derive Wasserstein Proximal Policy Gradient (WPPG)…

Machine Learning · Computer Science 2026-03-04 Zhaoyu Zhu , Shuhan Zhang , Rui Gao , Shuang Li

Deep Q-learning algorithms often suffer from poor gradient estimations with an excessive variance, resulting in unstable training and poor sampling efficiency. Stochastic variance-reduced gradient methods such as SVRG have been applied to…

Machine Learning · Computer Science 2020-07-28 Haonan Jia , Xiao Zhang , Jun Xu , Wei Zeng , Hao Jiang , Xiaohui Yan , Ji-Rong Wen

This paper considers policy search in continuous state-action reinforcement learning problems. Typically, one computes search directions using a classic expression for the policy gradient called the Policy Gradient Theorem, which decomposes…

Machine Learning · Computer Science 2020-04-13 Sujay Bhatt , Alec Koppel , Vikram Krishnamurthy

Iterative procedures for parameter estimation based on stochastic gradient descent allow the estimation to scale to massive data sets. However, in both theory and practice, they suffer from numerical instability. Moreover, they are…

Methodology · Statistics 2016-06-08 Panos Toulis , Dustin Tran , Edoardo M. Airoldi

We introduce a novel training procedure for policy gradient methods wherein episodic memory is used to optimize the hyperparameters of reinforcement learning algorithms on-the-fly. Unlike other hyperparameter searches, we formulate…

Machine Learning · Computer Science 2021-12-06 Hung Le , Majid Abdolshah , Thommen K. George , Kien Do , Dung Nguyen , Svetha Venkatesh

We consider solving a convex, possibly stochastic optimization problem over a randomly time-varying multi-agent network. Each agent has access to some local objective function, and it only has unbiased estimates of the gradients of the…

Optimization and Control · Mathematics 2016-11-29 Mingyi Hong , Tsung-Hui Chang

This paper proposes an accelerated proximal stochastic variance reduced gradient (ASVRG) method, in which we design a simple and effective momentum acceleration trick. Unlike most existing accelerated stochastic variance reduction methods…

Machine Learning · Computer Science 2018-11-20 Fanhua Shang , Licheng Jiao , Kaiwen Zhou , James Cheng , Yan Ren , Yufei Jin

We introduce new algorithms and convergence guarantees for privacy-preserving non-convex Empirical Risk Minimization (ERM) on smooth $d$-dimensional objectives. We develop an improved sensitivity analysis of stochastic gradient descent on…

Machine Learning · Computer Science 2022-10-13 Hoang Tran , Ashok Cutkosky

We examine the use of different randomisation policies for stochastic gradient algorithms used in sampling, based on first-order (or overdamped) Langevin dynamics, the most popular of which is known as Stochastic Gradient Langevin Dynamics.…

Numerical Analysis · Mathematics 2025-12-16 Luke Shaw , Peter A. Whalley

The softmax policy gradient (PG) method, which performs gradient ascent under softmax policy parameterization, is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. For $\gamma$-discounted…

Machine Learning · Computer Science 2022-12-19 Gen Li , Yuting Wei , Yuejie Chi , Yuxin Chen

One stream of reinforcement learning research is exploring biologically plausible models and algorithms to simulate biological intelligence and fit neuromorphic hardware. Among them, reward-modulated spike-timing-dependent plasticity…

Neural and Evolutionary Computing · Computer Science 2022-10-25 Zhile Yang , Shangqi Guo , Ying Fang , Jian K. Liu

Stateful policies play an important role in reinforcement learning, such as handling partially observable environments, enhancing robustness, or imposing an inductive bias directly into the policy structure. The conventional method for…

Machine Learning · Computer Science 2023-11-08 Firas Al-Hafez , Guoping Zhao , Jan Peters , Davide Tateo

In this paper, we propose a novel sufficient decrease technique for stochastic variance reduced gradient descent methods such as SVRG and SAGA. In order to make sufficient decrease for stochastic optimization, we design a new sufficient…

Machine Learning · Statistics 2018-02-28 Fanhua Shang , Yuanyuan Liu , Kaiwen Zhou , James Cheng , Kelvin K. W. Ng , Yuichi Yoshida

Many machine learning applications and tasks rely on the stochastic gradient descent (SGD) algorithm and its variants. Effective step length selection is crucial for the success of these algorithms, which has motivated the development of…

Machine Learning · Computer Science 2023-05-18 Shigeng Sun , Yuchen Xie

This paper studies a stochastic algorithm for linearly constrained nonconvex optimization, where the objective function is smooth but only unbiased stochastic gradients with bounded variance are available. We propose a momentum-based…

Optimization and Control · Mathematics 2026-04-16 Chenyang Qiu , Mihitha Maithripala , Zongli Lin

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

Despite extreme sample inefficiency, on-policy reinforcement learning, aka policy gradients, has become a fundamental tool in decision-making problems. With the recent advances in GPU-driven simulation, the ability to collect large amounts…

Machine Learning · Computer Science 2024-07-30 Jayesh Singla , Ananye Agarwal , Deepak Pathak

The use of momentum in stochastic gradient methods has become a widespread practice in machine learning. Different variants of momentum, including heavy-ball momentum, Nesterov's accelerated gradient (NAG), and quasi-hyperbolic momentum…

Machine Learning · Computer Science 2019-10-31 Igor Gitman , Hunter Lang , Pengchuan Zhang , Lin Xiao