Skip to Main content Skip to Navigation
Conference papers

Upper Confidence Trees with Short Term Partial Information

Olivier Teytaud 1, 2 Sébastien Flory 3
2 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/inria-00585475
Contributor : Olivier Teytaud <>
Submitted on : Tuesday, February 26, 2013 - 12:39:45 PM
Last modification on : Thursday, July 8, 2021 - 3:47:53 AM
Long-term archiving on: : Monday, May 27, 2013 - 6:40:11 AM

File

samcts.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Olivier Teytaud, Sébastien Flory. Upper Confidence Trees with Short Term Partial Information. EvoGames 2011, Apr 2011, Turino, Italy. pp.153-162, ⟨10.1007/978-3-642-20525-5⟩. ⟨inria-00585475v2⟩

Share

Metrics

Record views

519

Files downloads

883