Open AccessLeverage the Average: an Analysis of KL Regularization in Reinforcement Learning
Author(s) -
Nino Vieillard,
Tadashi Kozuno,
Bruno Scherrer,
Olivier Pietquin,
Rémi Munos,
Matthieu Geist
Publication year - 2020
Publication title -
hal (le centre pour la communication scientifique directe)
Language(s) - English
Resource type - Conference proceedings
Subject(s) - reinforcement learning , regularization (linguistics) , computer science , quadratic equation , leverage (statistics) , algorithm , entropy (arrow of time) , mathematical optimization , artificial intelligence , machine learning , mathematics , physics , geometry , quantum mechanics