Open AccessBilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration & Planning
Author(s) -
Reda Ouhamma,
Debabrota Basu,
Odalric-Ambrym Maillard
Publication year - 2022
Publication title -
hal (le centre pour la communication scientifique directe)
Language(s) - English
Resource type - Conference proceedings
Subject(s) - regret , frequentist inference , bilinear interpolation , computer science , exponential function , mathematical optimization , bayesian probability , mathematics , artificial intelligence , bayesian inference , machine learning , computer vision , mathematical analysis