An Analysis of a Simple Reinforcement Dynamics: Learning to Play an "Egalitarian" Equilibrium

A. Possajennikov

Research output: Working paperDiscussion paperOther research output

240 Downloads (Pure)

Abstract

The paper analyses a simple reinforcing dynamics. The dynamics can be interpreted as a learning dynamics with fixed aspiration level. All payoffs are assumed to be above this aspiration level, therefore all strategies are reinforcing. Different versions of the dynamics exhibit different convergence properties. The analysis starts with one-agent decision problems and proceeds to games. Some results are available for decision problems and simple games. For complex games computer simulations are performed. The hypothesis is that the dynamics favors an "egalitarian" equilibrium even if it does not satisfy other refinements.
Original languageEnglish
Place of PublicationTilburg
PublisherMicroeconomics
Number of pages26
Volume1997-19
Publication statusPublished - 1997

Publication series

NameCentER Discussion Paper
Volume1997-19

Fingerprint

Learning dynamics
Reinforcement
Aspiration Level
Computer simulation
Simple game

Keywords

  • Equilibrium selection
  • stochastic learning
  • bounded rationality

Cite this

Possajennikov, A. (1997). An Analysis of a Simple Reinforcement Dynamics: Learning to Play an "Egalitarian" Equilibrium. (CentER Discussion Paper; Vol. 1997-19). Tilburg: Microeconomics.
Possajennikov, A. / An Analysis of a Simple Reinforcement Dynamics : Learning to Play an "Egalitarian" Equilibrium. Tilburg : Microeconomics, 1997. (CentER Discussion Paper).
@techreport{d415ae0db06b4a639dcce58e86eb4084,
title = "An Analysis of a Simple Reinforcement Dynamics: Learning to Play an {"}Egalitarian{"} Equilibrium",
abstract = "The paper analyses a simple reinforcing dynamics. The dynamics can be interpreted as a learning dynamics with fixed aspiration level. All payoffs are assumed to be above this aspiration level, therefore all strategies are reinforcing. Different versions of the dynamics exhibit different convergence properties. The analysis starts with one-agent decision problems and proceeds to games. Some results are available for decision problems and simple games. For complex games computer simulations are performed. The hypothesis is that the dynamics favors an {"}egalitarian{"} equilibrium even if it does not satisfy other refinements.",
keywords = "Equilibrium selection, stochastic learning, bounded rationality",
author = "A. Possajennikov",
note = "Pagination: 26",
year = "1997",
language = "English",
volume = "1997-19",
series = "CentER Discussion Paper",
publisher = "Microeconomics",
type = "WorkingPaper",
institution = "Microeconomics",

}

Possajennikov, A 1997 'An Analysis of a Simple Reinforcement Dynamics: Learning to Play an "Egalitarian" Equilibrium' CentER Discussion Paper, vol. 1997-19, Microeconomics, Tilburg.

An Analysis of a Simple Reinforcement Dynamics : Learning to Play an "Egalitarian" Equilibrium. / Possajennikov, A.

Tilburg : Microeconomics, 1997. (CentER Discussion Paper; Vol. 1997-19).

Research output: Working paperDiscussion paperOther research output

TY - UNPB

T1 - An Analysis of a Simple Reinforcement Dynamics

T2 - Learning to Play an "Egalitarian" Equilibrium

AU - Possajennikov, A.

N1 - Pagination: 26

PY - 1997

Y1 - 1997

N2 - The paper analyses a simple reinforcing dynamics. The dynamics can be interpreted as a learning dynamics with fixed aspiration level. All payoffs are assumed to be above this aspiration level, therefore all strategies are reinforcing. Different versions of the dynamics exhibit different convergence properties. The analysis starts with one-agent decision problems and proceeds to games. Some results are available for decision problems and simple games. For complex games computer simulations are performed. The hypothesis is that the dynamics favors an "egalitarian" equilibrium even if it does not satisfy other refinements.

AB - The paper analyses a simple reinforcing dynamics. The dynamics can be interpreted as a learning dynamics with fixed aspiration level. All payoffs are assumed to be above this aspiration level, therefore all strategies are reinforcing. Different versions of the dynamics exhibit different convergence properties. The analysis starts with one-agent decision problems and proceeds to games. Some results are available for decision problems and simple games. For complex games computer simulations are performed. The hypothesis is that the dynamics favors an "egalitarian" equilibrium even if it does not satisfy other refinements.

KW - Equilibrium selection

KW - stochastic learning

KW - bounded rationality

M3 - Discussion paper

VL - 1997-19

T3 - CentER Discussion Paper

BT - An Analysis of a Simple Reinforcement Dynamics

PB - Microeconomics

CY - Tilburg

ER -

Possajennikov A. An Analysis of a Simple Reinforcement Dynamics: Learning to Play an "Egalitarian" Equilibrium. Tilburg: Microeconomics. 1997. (CentER Discussion Paper).