Mutual observability and the convergence of actions in a multi-person two-armed bandit model

DOI10.1006/jeth.1995.2450zbMath0916.90293OpenAlexW2087408416MaRDI QIDQ1276116

Masaki Aoyagi

Publication date: 30 June 1999

Published in: Journal of Economic Theory (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/18bf63a6c1f88a61476acec95b53d587584fa85e

zbMATH Keywords

experimentationherd behaviortwo-armed banditmutual observability

Mathematics Subject Classification ID

Probabilistic games; gambling (91A60)

Related Items (5)

On games of strategic experimentation ⋮ Learning in society ⋮ Endogenous supply of fiat money ⋮ Mutual observability and the convergence of actions in a multi-person two-armed bandit model ⋮ Stable repeated strategies for information exchange between two autonomous agents

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Subgame-perfect equilibria of finite- and infinite-horizon games
• Some extensions of a claim of Aumann in an axiomatic model of knowledge
• Bayesian learning in normal form games
• Mutual observability and the convergence of actions in a multi-person two-armed bandit model
• On the convergence of informational cascades
• Bayesian learning leads to correlated equilibria in normal form games
• Word-of-mouth learning.
• Bayesian learning in repeated games
• Rational Learning Leads to Nash Equilibrium
• Strategic Experimentation
• Word-of-Mouth Communication and Social Learning
• On the Asymptotic Behavior of Bayes' Estimates in the Discrete Case

This page was built for publication: Mutual observability and the convergence of actions in a multi-person two-armed bandit model