English
Related papers

Related papers: On Wasserstein Reinforcement Learning and the Fokk…

200 papers

Wasserstein gradient flows provide a powerful means of understanding and solving many diffusion equations. Specifically, Fokker-Planck equations, which model the diffusion of probability measures, can be understood as gradient descent over…

Machine Learning · Computer Science 2021-10-26 Petr Mokrov , Alexander Korotin , Lingxiao Li , Aude Genevay , Justin Solomon , Evgeny Burnaev

We study the Fokker-Planck equation as the hydrodynamic limit of a stochastic particle system on one hand and as a Wasserstein gradient flow on the other. We write the rate functional, that characterizes the large deviations from the…

Analysis of PDEs · Mathematics 2012-03-29 Manh Hong Duong , Vaios Laschos , Michiel Renger

We describe an application of Wasserstein distance to Reinforcement Learning. The Wasserstein distance in question is between the distribution of mappings of trajectories of a policy into some metric space, and some other fixed distribution…

Machine Learning · Computer Science 2019-08-01 Mohammed Amin Abdullah , Aldo Pacchiano , Moez Draief

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

Policy optimization is a core component of reinforcement learning (RL), and most existing RL methods directly optimize parameters of a policy based on maximizing the expected total reward, or its surrogate. Though often achieving…

Machine Learning · Computer Science 2018-08-10 Ruiyi Zhang , Changyou Chen , Chunyuan Li , Lawrence Carin

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 consider a class of time-homogeneous diffusion processes on $\mathbb{R}^{n}$ with common invariant measure but varying volatility matrices. In Euclidean space, we show via stochastic control of the diffusion coefficient that the…

Probability · Mathematics 2023-10-31 Bertram Tschiderer

Off-policy evaluation and learning are concerned with assessing a given policy and learning an optimal policy from offline data without direct interaction with the environment. Often, the environment in which the data are collected differs…

Machine Learning · Computer Science 2024-01-18 Yi Shen , Pan Xu , Michael M. Zavlanos

Wasserstein Policy Optimization (WPO) is a recently proposed reinforcement learning algorithm that leverages Wasserstein gradient flows to optimize stochastic policies in continuous action spaces. Despite its empirical success, the…

Machine Learning · Computer Science 2026-05-22 David Šiška , Yufei Zhang

We consider a Fokker-Planck equation which is coupled to an externally given time-dependent constraint on its first moment. This constraint introduces a Lagrange-multiplier which renders the equation nonlocal and nonlinear. In this paper we…

Analysis of PDEs · Mathematics 2018-11-28 Simon Eberle , Barbara Niethammer , André Schlichting

We revisit the variational characterization of diffusion as entropic gradient flux and provide for it a probabilistic interpretation based on stochastic calculus. It was shown by Jordan, Kinderlehrer, and Otto that, for diffusions of…

Probability · Mathematics 2020-03-24 Ioannis Karatzas , Walter Schachermayer , Bertram Tschiderer

We introduce Wasserstein Policy Optimization (WPO), an actor-critic algorithm for reinforcement learning in continuous action spaces. WPO can be derived as an approximation to Wasserstein gradient flow over the space of all policies…

Machine Learning · Computer Science 2025-05-02 David Pfau , Ian Davies , Diana Borsa , Joao G. M. Araujo , Brendan Tracey , Hado van Hasselt

We study the large deviation rate functional for the empirical distribution of independent Brownian particles with drift. In one dimension, it has been shown by Adams, Dirr, Peletier and Zimmer that this functional is asymptotically…

Probability · Mathematics 2016-01-11 Matthias Erbar , Jan Maas , Michiel Renger

To ensure stability of learning, state-of-the-art generalized policy iteration algorithms augment the policy improvement step with a trust region constraint bounding the information loss. The size of the trust region is commonly determined…

Machine Learning · Computer Science 2018-04-05 Boris Belousov , Jan Peters

In this paper we identify the Fokker-Planck equation for (reflected) Sticky Brownian Motion as a Wasserstein gradient flow in the space of probability measures. The driving functional is the relative entropy with respect to a non-standard…

Analysis of PDEs · Mathematics 2025-01-27 Jean-Baptiste Casteras , Léonard Monsaingeon , Filippo Santambrogio

Robust Reinforcement Learning aims to find the optimal policy with some extent of robustness to environmental dynamics. Existing learning algorithms usually enable the robustness through disturbing the current state or simulating…

Machine Learning · Computer Science 2020-06-02 Linfang Hou , Liang Pang , Xin Hong , Yanyan Lan , Zhiming Ma , Dawei Yin

Gradient flows of the Kullback--Leibler (KL) divergence, such as the Fokker--Planck equation and Stein Variational Gradient Descent, evolve a distribution toward a target density known only up to a normalizing constant. We introduce new…

Machine Learning · Statistics 2026-02-09 Elias Hess-Childs , Dejan Slepčev , Lantian Xu

In this work, we investigate a variational formulation for a time-fractional Fokker-Planck equation which arises in the study of complex physical systems involving anomalously slow diffusion. The model involves a fractional-order Caputo…

Numerical Analysis · Mathematics 2020-06-05 Manh Hong Duong , Bangti Jin

Trust-region methods based on Kullback-Leibler divergence are pervasively used to stabilize policy optimization in reinforcement learning. In this paper, we exploit more flexible metrics and examine two natural extensions of policy…

Machine Learning · Computer Science 2023-06-27 Jun Song , Niao He , Lijun Ding , Chaoyue Zhao

The steady state of the Fokker-Planck equation corresponding to a density dependent one-step process is approximated by a suitable normal distribution. Starting from the master equations of the process, written in terms of the time…

Dynamical Systems · Mathematics 2016-09-16 Peter L. Simon , Eszter Sikolya
‹ Prev 1 2 3 10 Next ›