Learning in the Presence of Noise

Panayotis Mertikopoulos 1 Aris L. Moustakas 2
1 MESCAL - Middleware efficiently scalable
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
Abstract : We investigate the emergence of rationality in repeated games where, at each iteration, the players' payoffs are randombly perturbed (to account e.g. for the effects of fading or errors in the reading of one's throughput). We see that even if players start out completely uneducated about the game, there is a simple learning scheme that enables them to eventually weed out the noise and identify suboptimal choices, regardless of the noise level. More precisely, we show that strategies that are strictly dominated (even iteratively) become extinct in the long run, i.e. players exhibit rational behavior. As an application, we model a number of users that are able to switch dynamically between multiple wireless nodes and see that they are able to pick up which node works best for them, even in the presence of high performance fluctuations.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01382307
Contributor : Panayotis Mertikopoulos <>
Submitted on : Sunday, October 16, 2016 - 3:29:27 PM
Last modification on : Thursday, November 8, 2018 - 2:28:04 PM

Identifiers

  • HAL Id : hal-01382307, version 1

Collections

Citation

Panayotis Mertikopoulos, Aris L. Moustakas. Learning in the Presence of Noise. GameNets '09: Proceedings of the 1st International Conference on Game Theory for Networks, 2009, Unknown, Unknown Region. ⟨hal-01382307⟩

Share

Metrics

Record views

183