Latest revision as of 17:53, 17 January 2019

Home * People * Rémi Munos

Rémi Munos ^[1]

Rémi Munos,
a French mathematician and computer scientist at Google DeepMind, from 2000 to 2006 Associate Professor at the Centre de Mathématiques Appliquées, Ecole Polytechnique and later affiliated with INRIA Lille ^[2]. His research interests covers reinforcement learning, multi-armed bandits, and dynamic programming. Rémi Muno was contributor of the Go playing program Mogo, using Monte-Carlo Tree Search which uses patterns in the simulations and improvements in UCT.

Selected Publications

Rémi Munos (1996). A convergent reinforcement learning algorithm in the continuous case : the finite-element reinforcement learning. In International Conference on Machine Learning. Morgan Kaufmann

Sylvain Gelly, Yizao Wang, Rémi Munos, Olivier Teytaud (2006). Modiﬁcation of UCT with Patterns in Monte-Carlo Go. INRIA
Jean-Yves Audibert, Rémi Munos, Csaba Szepesvári (2007). Tuning Bandit Algorithms in Stochastic Environments. pdf
Yizao Wang, Jean-Yves Audibert, Rémi Munos (2008). Algorithms for Infinitely Many-Armed Bandits, , Advances in Neural Information Processing Systems, pdf, Supplemental material - pdf
Rémi Munos, Csaba Szepesvári (2008). Finite time bounds for sampling based fitted value iteration. Journal of Machine Learning Research, 9:815-857, 2008. pdf, pdf
Raphaël Maîtrepierre, Jérémie Mary, Rémi Munos (2008). Adaptive play in Texas Hold'em Poker. ECAI 2008
Jean-Yves Audibert, Rémi Munos, Csaba Szepesvári (2009). Exploration-exploitation trade-off using variance estimates in multi-armed bandits. Theoretical Computer Science, 410:1876-1902, 2009, pdf
Vincent Berthier, Amine Bourki, Matthieu Coulm, Guillaume Chaslot, Christophe Fiter, Sylvain Gelly, Jean-Baptiste Hoock, Rémi Munos, Julien Pérez, Arpad Rimmel, Philippe Rolet, Olivier Teytaud, Paul Vayssière, Yizao Wang, Ziqin Yu (et al.) (2009). Computer-Go is not only for Go. Korea, August 2009 slides as pdf

Rémi Munos (2010). Approximate dynamic programming. In Olivier Sigaud and Olivier Buffet, editors, Markov Decision Processes in Artificial Intelligence, chapter 3, pages 67-98. ISTE Ltd and John Wiley & Sons Inc., pdf
Ronald Ortner, Daniil Ryabko, Peter Auer, Rémi Munos (2014). Regret bounds for restless Markov bandits. Theoretical Computer Science 558, pdf
Rémi Munos (2014). From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning. Foundations and Trends in Machine Learning, Vol. 7, No 1, hal-00747575v5, slides as pdf
Tor Lattimore, Rémi Munos (2014). Bounded Regret for Finite-Armed Structured Bandits. arXiv:1411.2919

@@ Line 22: / Line 22: @@
 * [[Mathematician#ROrtner|Ronald Ortner]], [[Mathematician#DRyabko|Daniil Ryabko]], [[Peter Auer]], [[Rémi Munos]] ('''2014'''). ''Regret bounds for restless Markov bandits''. [https://en.wikipedia.org/wiki/Theoretical_Computer_Science_%28journal%29 Theoretical Computer Science] 558, [http://daniil.ryabko.net/mabajr.pdf pdf]
 * [[Rémi Munos]] ('''2014'''). ''From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning''. [http://dblp.uni-trier.de/db/journals/ftml/ftml7.html#Munos14 Foundations and Trends in Machine Learning, Vol. 7, No 1], [https://hal.archives-ouvertes.fr/hal-00747575 hal-00747575v5], [http://chercheurs.lille.inria.fr/~munos/papers/files/AAAI2013_slides.pdf slides as pdf]
+* [[Tor Lattimore]], [[Rémi Munos]] ('''2014'''). ''Bounded Regret for Finite-Armed Structured Bandits''. [https://arxiv.org/abs/1411.2919 arXiv:1411.2919]
 ==2015 ...==
 * [[Audrūnas Gruslys]], [[Rémi Munos]], [[Ivo Danihelka]], [[Marc Lanctot]], [[Alex Graves]] ('''2016'''). ''Memory-Efficient Backpropagation Through Time''. [https://arxiv.org/abs/1606.03401v1 arXiv:1606.03401]