Open AccessSoftened approximate policy iteration for Markov games
Author(s) -
Julien Pérolat,
Bilal Piot,
Matthieu Geist,
Bruno Scherrer,
Olivier Pietquin
Publication year - 2016
Publication title -
hal (le centre pour la communication scientifique directe)
Language(s) - Uncategorized
Resource type - Conference proceedings
Subject(s) - computer science , residual , mathematical optimization , markov decision process , norm (philosophy) , minification , stability (learning theory) , markov chain , algorithm , markov process , mathematics , machine learning , statistics , political science , law