• français
    • English
  • English 
    • français
    • English
  • Login
JavaScript is disabled for your browser. Some features of this site may not work without it.
BIRD Home

Browse

This CollectionBy Issue DateAuthorsTitlesSubjectsJournals BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesSubjectsJournals

My Account

Login

Statistics

View Usage Statistics

Learning Agents for Iterative Voting

Thumbnail
Date
2017
Notes
Lecture Notes in Computer Science book series (LNCS, volume 10576)
Dewey
Recherche opérationnelle
Sujet
Computational social choice; Iterative voting; Bandit algorithms
DOI
http://dx.doi.org/10.1007/978-3-319-67504-6_10
Conference name
5th International Conference (ADT 2017)
Conference date
10-2017
Conference city
Luxembourg
Conference country
Luxembourg
Book title
Algorithmic Decision Theory - 5th International Conference (ADT 2017)
Author
Rothe, Jörg
Publisher
Springer International Publishing
Publisher city
Berlin Heidelberg
Year
09-2017
Pages number
390
ISBN
978-3-319-67503-9
Book URL
10.1007/978-3-319-67504-6
URI
https://basepub.dauphine.fr/handle/123456789/18587
Collections
  • LAMSADE : Publications
Metadata
Show full item record
Author
Airiau, Stéphane
989 Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Grandi, Umberto
status unknown
Studzinski Perotto, Filipo
status unknown
Type
Communication / Conférence
Item number of pages
139-152
Abstract (EN)
This paper assesses the learning capabilities of agents in a situation of collective choice. Each agent is endowed with a private preference concerning a number of alternative candidates, and participates in an iterated plurality election. Agents get rewards depending on the winner of each election, and adjust their voting strategy using reinforcement learning. By conducting extensive simulations, we show that our agents are capable of learning how to take decisions at the level of well-known voting procedures, and that these decisions maintain good choice-theoretic properties when increasing the number of agents or candidates.

  • Accueil Bibliothèque
  • Site de l'Université Paris-Dauphine
  • Contact
SCD Paris Dauphine - Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16

 Content on this site is licensed under a Creative Commons 2.0 France (CC BY-NC-ND 2.0) license.