A geometric embedding approach to multiple games and multiple populations

[PDF] arxiv.org

Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients

J Müller, S Çaycı, G Montúfar - arXiv preprint arXiv:2403.19448, 2024 - arxiv.org
Kakade's natural policy gradient method has been studied extensively in the last years
showing linear convergence with and without regularization. We study another natural …
被引用次数：2 相关文章 所有 2 个版本
[PDF] arxiv.org

Generative Assignment Flows for Representing and Learning Joint Distributions of Discrete Data

B Boll, D Gonzalez-Alvarado, S Petra… - arXiv preprint arXiv …, 2024 - arxiv.org
We introduce a novel generative model for the representation of joint probability distributions
of a possibly large number of discrete random variables. The approach uses measure …
被引用次数：1 相关文章 所有 4 个版本
[PDF] arxiv.org

Sigma Flows for Image and Data Labeling and Learning Structured Prediction

J Cassel, B Boll, S Petra, P Albers… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper introduces the sigma flow model for the prediction of structured labelings of data
observed on Riemannian manifolds, including Euclidean image domains as special case …
相关文章 所有 2 个版本
[PDF] arxiv.org

Essentially Sharp Estimates on the Entropy Regularization Error in Discrete Discounted Markov Decision Processes

J Müller, S Cayci - arXiv preprint arXiv:2406.04163, 2024 - arxiv.org
We study the error introduced by entropy regularization of infinite-horizon discrete
discounted Markov decision processes. We show that this error decreases exponentially in …
相关文章 所有 3 个版本