English
Related papers

Related papers: Policy Gradient with Second Order Momentum

200 papers

Policy gradient (PG) methods are the backbone of many reinforcement learning algorithms due to their good performance in policy optimization problems. As a gradient-based approach, PG methods typically rely on knowledge of the system…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Bowen Song , Andrea Iannelli

Reinforcement learning is a promising approach to learning robotics controllers. It has recently been shown that algorithms based on finite-difference estimates of the policy gradient are competitive with algorithms based on the policy…

Machine Learning · Computer Science 2021-10-12 Osbert Bastani

Approaches to policy optimization have been motivated from diverse principles, based on how the parametric model is interpreted (e.g. value versus policy representation) or how the learning objective is formulated, yet they share a common…

Machine Learning · Computer Science 2022-06-20 Ramki Gummadi , Saurabh Kumar , Junfeng Wen , Dale Schuurmans

Distortion Risk Measures (DRMs) capture risk preferences in decision-making and serve as general criteria for managing uncertainty. This paper proposes gradient descent algorithms for DRM optimization based on two dual representations: the…

Machine Learning · Computer Science 2025-10-07 Jinyang Jiang , Bernd Heidergott , Jiaqiao Hu , Yijie Peng

We consider stochastic convex optimization problems where the objective is an expectation over smooth functions. For this setting we suggest a novel gradient estimate that combines two recent mechanism that are related to notion of…

Machine Learning · Computer Science 2025-03-06 Tehila Dahan , Kfir Y. Levy

A consequent approach is proposed to construct symplectic force-gradient algorithms of arbitrarily high orders in the time step for precise integration of motion in classical and quantum mechanics simulations. Within this approach the basic…

Statistical Mechanics · Physics 2009-11-07 Igor Omelyan , Ihor Mryglod , Reinhard Folk

In this paper, we propose a second-order deterministic actor-critic framework in reinforcement learning that extends the classical deterministic policy gradient method to exploit curvature information of the performance function. Building…

Machine Learning · Computer Science 2025-11-13 Arash Bahari Kordabad , Dean Brandner , Sebastien Gros , Sergio Lucia , Sadegh Soudjani

We propose a novel stochastic optimization algorithm called STOchastic Recursive Momentum for Compositional (STORM-Compositional) optimization that minimizes the composition of expectations of two stochastic functions, the latter being an…

Optimization and Control · Mathematics 2020-06-09 Huizhuo Yuan , Wenqing Hu

A common optimization tool used in deep reinforcement learning is momentum, which consists in accumulating and discounting past gradients, reapplying them at each iteration. We argue that, unlike in supervised learning, momentum in Temporal…

Machine Learning · Computer Science 2021-06-09 Emmanuel Bengio , Joelle Pineau , Doina Precup

First-order methods such as stochastic gradient descent (SGD) are currently the standard algorithm for training deep neural networks. Second-order methods, despite their better convergence rate, are rarely used in practice due to the…

Machine Learning · Computer Science 2019-09-26 Tianle Cai , Ruiqi Gao , Jikai Hou , Siyu Chen , Dong Wang , Di He , Zhihua Zhang , Liwei Wang

For a large class of variational quantum circuits, we show how arbitrary-order derivatives can be analytically evaluated in terms of simple parameter-shift rules, i.e., by running the same circuit with different shifts of the parameters. As…

Quantum Physics · Physics 2021-03-03 Andrea Mari , Thomas R. Bromley , Nathan Killoran

In this paper, we consider the problem of learning safe policies for probabilistic-constrained reinforcement learning (RL). Specifically, a safe policy or controller is one that, with high probability, maintains the trajectory of the agent…

Machine Learning · Computer Science 2024-03-14 Weiqin Chen , Dharmashankar Subramanian , Santiago Paternain

This work studies minimization problems with zero-order noisy oracle information under the assumption that the objective function is highly smooth and possibly satisfies additional properties. We consider two kinds of zero-order projected…

Statistics Theory · Mathematics 2023-06-06 Arya Akhavan , Evgenii Chzhen , Massimiliano Pontil , Alexandre B. Tsybakov

The goal of policy-based reinforcement learning (RL) is to search the maximal point of its objective. However, due to the inherent non-concavity of its objective, convergence to a first-order stationary point (FOSP) can not guarantee the…

Machine Learning · Computer Science 2020-12-04 Long Yang , Qian Zheng , Gang Pan

A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behavior to unseen goals, such policies may also enable…

Machine Learning · Computer Science 2019-02-21 Paulo Rauber , Avinash Ummadisingu , Filipe Mutz , Juergen Schmidhuber

In stochastic gradient descent, especially for neural network training, there are currently dominating first order methods: not modeling local distance to minimum. This information required for optimal step size is provided by second order…

Machine Learning · Computer Science 2019-12-10 Jarek Duda

Policy gradient methods are an appealing approach in reinforcement learning because they directly optimize the cumulative reward and can straightforwardly be used with nonlinear function approximators such as neural networks. The two main…

Machine Learning · Computer Science 2018-10-23 John Schulman , Philipp Moritz , Sergey Levine , Michael Jordan , Pieter Abbeel

We introduce a new approach for comparing reinforcement learning policies, using Wasserstein distances (WDs) in a newly defined latent behavioral space. We show that by utilizing the dual formulation of the WD, we can learn score functions…

Machine Learning · Computer Science 2020-03-05 Aldo Pacchiano , Jack Parker-Holder , Yunhao Tang , Anna Choromanska , Krzysztof Choromanski , Michael I. Jordan

We present new policy mirror descent (PMD) methods for solving reinforcement learning (RL) problems with either strongly convex or general convex regularizers. By exploring the structural properties of these overall highly nonconvex…

Machine Learning · Computer Science 2022-04-08 Guanghui Lan

This paper considers decentralized dynamic optimization problems where nodes of a network try to minimize a sequence of time-varying objective functions in a real-time scheme. At each time slot, nodes have access to different summands of an…

Optimization and Control · Mathematics 2016-03-29 Aryan Mokhtari , Wei Shi , Qing Ling , Alejandro Ribeiro
‹ Prev 1 8 9 10 Next ›