Skip to Main content Skip to Navigation
Conference papers

Hedging Algorithms and Repeated Matrix Games

Abstract : Playing repeated matrix games (RMG) while maximizing the cumulative returns is a basic method to evaluate multi-agent learning (MAL) algorithms. Previous work has shown that UCB, M3, S or Exp3 algorithms have good behaviors on average in RMG. Besides, hedging algorithms have been shown to be effective on prediction problems. An hedging algorithm is made up with a top-level algorithm and a set of basic algorithms. To make its decision, an hedging algorithm uses its top-level algorithm to choose a basic algorithm, and the chosen algorithm makes the decision. This paper experimentally shows that well-selected hedging algorithms are better on average than all previous MAL algorithms on the task of playing RMG against various players. S is a very good top-level algorithm, and UCB and M3 are very good basic algorithms. Furthermore, two-level hedging algorithms are more effective than one-level hedging algorithms, and three levels are not better than two levels.
Document type :
Conference papers
Complete list of metadata

Cited literature [24 references]  Display  Hide  Download

https://hal.inria.fr/hal-00975943
Contributor : Damien Pellier <>
Submitted on : Wednesday, April 9, 2014 - 1:29:22 PM
Last modification on : Friday, April 10, 2020 - 5:29:31 PM
Long-term archiving on: : Wednesday, July 9, 2014 - 12:11:11 PM

File

bouzy11.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00975943, version 1

Citation

Bruno Bouzy, Marc Métivier, Damien Pellier. Hedging Algorithms and Repeated Matrix Games. Workshop on Machine Learning and Data Mining in and around Games (ECML-PKDD), Sep 2011, Athens, Greece. ⟨hal-00975943⟩

Share

Metrics

Record views

281

Files downloads

310