Web: http://arxiv.org/abs/2201.07296

June 17, 2022, 1:11 a.m. | Bekzhan Kerimkulov, James-Michael Leahy, David Šiška, Lukasz Szpruch

cs.LG updates on arXiv.org arxiv.org

We study the global convergence of policy gradient for infinite-horizon,
continuous state and action space, and entropy-regularized Markov decision
processes (MDPs). We consider a softmax policy with (one-hidden layer) neural
network approximation in a mean-field regime. Additional entropic
regularization in the associated mean-field probability measure is added, and
the corresponding gradient flow is studied in the 2-Wasserstein metric. We show
that the objective function is increasing along the gradient flow. Further, we
prove that if the regularization in terms of …

approximation arxiv convergence entropy gradient math mean network neural neural network policy

More from arxiv.org / cs.LG updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY