Upper Confidence Trees with Short Term Partial Information
Résumé
We show some mathematical links between partially observable (PO) games in which information is regu larly revealed, and simultaneous actions games. Using this, we study the extension of Monte-Carlo Tr ee Search algorithms to PO games and to games with simultaneous actions. We apply the results to Urb an Rivals, a free PO internet card game with more than 10 millions of registered users.
Domaines
Optimisation et contrôle [math.OC]Origine | Fichiers produits par l'(les) auteur(s) |
---|