Home > Research > Publications & Outputs > Generalised weakened fictitious play
View graph of relations

Generalised weakened fictitious play

Research output: Contribution to journalJournal articlepeer-review

Published

Standard

Generalised weakened fictitious play. / Leslie, David S.; Collins, E. J.

In: Games and Economic Behavior, Vol. 56, No. 2, 01.08.2006, p. 285-298.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Leslie, DS & Collins, EJ 2006, 'Generalised weakened fictitious play', Games and Economic Behavior, vol. 56, no. 2, pp. 285-298. https://doi.org/10.1016/j.geb.2005.08.005

APA

Leslie, D. S., & Collins, E. J. (2006). Generalised weakened fictitious play. Games and Economic Behavior, 56(2), 285-298. https://doi.org/10.1016/j.geb.2005.08.005

Vancouver

Leslie DS, Collins EJ. Generalised weakened fictitious play. Games and Economic Behavior. 2006 Aug 1;56(2):285-298. https://doi.org/10.1016/j.geb.2005.08.005

Author

Leslie, David S. ; Collins, E. J. / Generalised weakened fictitious play. In: Games and Economic Behavior. 2006 ; Vol. 56, No. 2. pp. 285-298.

Bibtex

@article{e7a4867d0c684d48b9c4b2850208f7ce,
title = "Generalised weakened fictitious play",
abstract = "A general class of adaptive processes in games is developed, which significantly generalises weakened fictitious play [Van der Genugten, B., 2000. A weakened form of fictitious play in two-person zero-sum games. Int. Game Theory Rev. 2, 307–328] and includes several interesting fictitious-play-like processes as special cases. The general model is rigorously analysed using the best response differential inclusion, and shown to converge in games with the fictitious play property. Furthermore, a new actor–critic process is introduced, in which the only information given to a player is the reward received as a result of selecting an action—a player need not even know they are playing a game. It is shown that this results in a generalised weakened fictitious play process, and can therefore be considered as a first step towards explaining how players might learn to play Nash equilibrium strategies without having any knowledge of the game, or even that they are playing a game.",
keywords = "Fictitious play, Best response differential inclusion, Stochastic approximation, Actor–critic process",
author = "Leslie, {David S.} and Collins, {E. J.}",
year = "2006",
month = aug,
day = "1",
doi = "10.1016/j.geb.2005.08.005",
language = "English",
volume = "56",
pages = "285--298",
journal = "Games and Economic Behavior",
issn = "0899-8256",
publisher = "ELSEVIER ACADEMIC PRESS INC",
number = "2",

}

RIS

TY - JOUR

T1 - Generalised weakened fictitious play

AU - Leslie, David S.

AU - Collins, E. J.

PY - 2006/8/1

Y1 - 2006/8/1

N2 - A general class of adaptive processes in games is developed, which significantly generalises weakened fictitious play [Van der Genugten, B., 2000. A weakened form of fictitious play in two-person zero-sum games. Int. Game Theory Rev. 2, 307–328] and includes several interesting fictitious-play-like processes as special cases. The general model is rigorously analysed using the best response differential inclusion, and shown to converge in games with the fictitious play property. Furthermore, a new actor–critic process is introduced, in which the only information given to a player is the reward received as a result of selecting an action—a player need not even know they are playing a game. It is shown that this results in a generalised weakened fictitious play process, and can therefore be considered as a first step towards explaining how players might learn to play Nash equilibrium strategies without having any knowledge of the game, or even that they are playing a game.

AB - A general class of adaptive processes in games is developed, which significantly generalises weakened fictitious play [Van der Genugten, B., 2000. A weakened form of fictitious play in two-person zero-sum games. Int. Game Theory Rev. 2, 307–328] and includes several interesting fictitious-play-like processes as special cases. The general model is rigorously analysed using the best response differential inclusion, and shown to converge in games with the fictitious play property. Furthermore, a new actor–critic process is introduced, in which the only information given to a player is the reward received as a result of selecting an action—a player need not even know they are playing a game. It is shown that this results in a generalised weakened fictitious play process, and can therefore be considered as a first step towards explaining how players might learn to play Nash equilibrium strategies without having any knowledge of the game, or even that they are playing a game.

KW - Fictitious play

KW - Best response differential inclusion

KW - Stochastic approximation

KW - Actor–critic process

U2 - 10.1016/j.geb.2005.08.005

DO - 10.1016/j.geb.2005.08.005

M3 - Journal article

VL - 56

SP - 285

EP - 298

JO - Games and Economic Behavior

JF - Games and Economic Behavior

SN - 0899-8256

IS - 2

ER -