Negatively Correlated Bandits

Arbeitspapier

We analyze a two-player game of strategic experimentation with two-armed bandits. Each player has to decide in continuous time whether to use a safe arm with a known payoff or a risky arm whose likelihood of delivering payoffs is initially unknown. The quality of the risky arms is perfectly negatively correlated between players. In marked contrast to the case where both risky arms are of the same type, we find that learn- ing will be complete in any Markov perfect equilibrium if the stakes exceed a certain threshold, and that all equilibria are in cutoff strategies. For low stakes, the equilib- rium is unique, symmetric, and coincides with the planner's solution. For high stakes, the equilibrium is unique, symmetric, and tantamount to myopic behavior. For inter- mediate stakes, there is a continuum of equilibria.

Angaben zum Objekt

• Sprache: Englisch

Verweise und Beziehungen

• Erschienen in: Series: SFB/TR 15 Discussion Paper ; No. 243

Klassifikation und Themen

• Klassifikation: Wirtschaft ; Stochastic and Dynamic Games; Evolutionary Games; Repeated Games ; Search; Learning; Information and Knowledge; Communication; Belief; Unawareness ; Management of Technological Innovation and R&D
• Thema: Strategic Experimentation ; Two-Armed Bandit ; Exponential Distribution ; Poisson Process ; Bayesian Learning ; Markov Perfect Equilibrium

Beteiligte, Orts- und Zeitangaben

• Ereignis: Geistige Schöpfung
• (wer): Klein, Nicolas ; Rady, Sven
• Ereignis: Veröffentlichung
• (wer): Sonderforschungsbereich/Transregio 15 - Governance and the Efficiency of Economic Systems (GESY)
• (wo): München
• (wann): 2008

Weitere Informationen

• DOI: doi:10.5282/ubm/epub.13309
• Handle: http://hdl.handle.net/10419/93959
• URN: urn:nbn:de:bvb:19-epub-13309-9
• Letzte Aktualisierung: 10.03.2025, 11:44 MEZ