Airiau, Stéphane and Grandi, Umberto and Studzinski Perotto, Filipo
Learning agents for iterative voting.
(2017)
In: International Conference on Algorithmic Decision Theory (ADT 2017), 29 October 2017 (Luxembourg, Luxembourg).
|
(Document in English)
PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader 345kB |
Official URL: https://doi.org/10.1007/978-3-319-67504-6_10
Abstract
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.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Additional Information: | Bibliographic references: Airiau S., Grandi U., Perotto F.S. (2017) Learning Agents for Iterative Voting. In: Rothe J. (eds) Algorithmic Decision Theory. ADT 2017, (Lecture Notes in Computer Science, vol 10576), Springer, Cham |
HAL Id: | hal-02641165 |
Audience (conference): | International conference proceedings |
Uncontrolled Keywords: | |
Institution: | French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE) Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE) Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE) Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE) Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE) Other partners > Université Paris-Dauphine (FRANCE) |
Laboratory name: | |
Statistics: | download |
Deposited On: | 14 May 2020 12:58 |
Repository Staff Only: item control page