Inventing New Signals

Jason McKenzie Alexander; Brian Skyrms; Sandy L. Zabell

doi:10.1007/s13235-011-0027-2

Inventing New Signals

Jason McKenzie Alexander, Brian Skyrms^*, Sandy L. Zabell

^*Corresponding author for this work

Mathematics

Research output: Contribution to journal › Article › peer-review

25 Scopus citations

Abstract

A model for inventing new signals is introduced in the context of sender-receiver games with reinforcement learning. If the invention parameter is set to zero, it reduces to basic Roth-Erev learning applied to acts rather than strategies, as in Argiento et al. (Stoch. Process. Appl. 119:373-390, 2009). If every act is uniformly reinforced in every state it reduces to the Chinese Restaurant Process-also known as the Hoppe-Pólya urn-applied to each act. The dynamics can move players from one signaling game to another during the learning process. Invention helps agents avoid pooling and partial pooling equilibria.

Original language	English (US)
Pages (from-to)	129-145
Number of pages	17
Journal	Dynamic Games and Applications
Volume	2
Issue number	1
DOIs	https://doi.org/10.1007/s13235-011-0027-2
State	Published - Mar 2012

Keywords

Chinese Restaurant Process
Hoppe-Pólya urn
Invention
Reinforcement
Signals

ASJC Scopus subject areas

Statistics and Probability
Economics and Econometrics
Computer Science Applications
Computer Graphics and Computer-Aided Design
Computational Theory and Mathematics
Computational Mathematics
Applied Mathematics

Access to Document

10.1007/s13235-011-0027-2

Cite this

@article{536c665daf634433b9c784f08eff12d4,

title = "Inventing New Signals",

abstract = "A model for inventing new signals is introduced in the context of sender-receiver games with reinforcement learning. If the invention parameter is set to zero, it reduces to basic Roth-Erev learning applied to acts rather than strategies, as in Argiento et al. (Stoch. Process. Appl. 119:373-390, 2009). If every act is uniformly reinforced in every state it reduces to the Chinese Restaurant Process-also known as the Hoppe-P{\'o}lya urn-applied to each act. The dynamics can move players from one signaling game to another during the learning process. Invention helps agents avoid pooling and partial pooling equilibria.",

keywords = "Chinese Restaurant Process, Hoppe-P{\'o}lya urn, Invention, Reinforcement, Signals",

author = "{McKenzie Alexander}, Jason and Brian Skyrms and Zabell, {Sandy L.}",

year = "2012",

month = mar,

doi = "10.1007/s13235-011-0027-2",

language = "English (US)",

volume = "2",

pages = "129--145",

journal = "Dynamic Games and Applications",

issn = "2153-0785",

publisher = "Springer Science + Business Media",

number = "1",

}

TY - JOUR

T1 - Inventing New Signals

AU - McKenzie Alexander, Jason

AU - Skyrms, Brian

AU - Zabell, Sandy L.

PY - 2012/3

Y1 - 2012/3

N2 - A model for inventing new signals is introduced in the context of sender-receiver games with reinforcement learning. If the invention parameter is set to zero, it reduces to basic Roth-Erev learning applied to acts rather than strategies, as in Argiento et al. (Stoch. Process. Appl. 119:373-390, 2009). If every act is uniformly reinforced in every state it reduces to the Chinese Restaurant Process-also known as the Hoppe-Pólya urn-applied to each act. The dynamics can move players from one signaling game to another during the learning process. Invention helps agents avoid pooling and partial pooling equilibria.

AB - A model for inventing new signals is introduced in the context of sender-receiver games with reinforcement learning. If the invention parameter is set to zero, it reduces to basic Roth-Erev learning applied to acts rather than strategies, as in Argiento et al. (Stoch. Process. Appl. 119:373-390, 2009). If every act is uniformly reinforced in every state it reduces to the Chinese Restaurant Process-also known as the Hoppe-Pólya urn-applied to each act. The dynamics can move players from one signaling game to another during the learning process. Invention helps agents avoid pooling and partial pooling equilibria.

KW - Chinese Restaurant Process

KW - Hoppe-Pólya urn

KW - Invention

KW - Reinforcement

KW - Signals

UR - http://www.scopus.com/inward/record.url?scp=84869221283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869221283&partnerID=8YFLogxK

U2 - 10.1007/s13235-011-0027-2

DO - 10.1007/s13235-011-0027-2

M3 - Article

AN - SCOPUS:84869221283

VL - 2

SP - 129

EP - 145

JO - Dynamic Games and Applications

JF - Dynamic Games and Applications

SN - 2153-0785

IS - 1

ER -

Inventing New Signals

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this