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 learning 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 equilibrium is unique, symmetric, and coincides with the planner's solution. For high stakes, the equilibrium is unique, symmetric, and tantamount to myopic behavior. For intermediate stakes, there is a continuum of equilibria.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: Munich Discussion Paper ; No. 2008-16

Classification and Topics

• Classification: Wirtschaft ; Stochastic and Dynamic Games; Evolutionary Games; Repeated Games ; Search; Learning; Information and Knowledge; Communication; Belief; Unawareness ; Public Goods ; Management of Technological Innovation and R&D
• Subject: Strategic Experimentation ; Two-Armed Bandit ; Exponential Distribution ; Poisson Process ; Bayesian Learning ; Markov Perfect Equilibrium ; Entscheidung bei Risiko ; Erwartungstheorie ; Gewinn ; Lernen ; Markovscher Prozess ; Spieltheorie

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Klein, Nicolas ; Rady, Sven
• Event: Veröffentlichung
• (who): Ludwig-Maximilians-Universität München, Volkswirtschaftliche Fakultät
• (where): München
• (when): 2008

Further information

• DOI: doi:10.5282/ubm/epub.5332
• Handle: http://hdl.handle.net/10419/104273
• URN: urn:nbn:de:bvb:19-epub-5332-0
• Last update: 10.03.2025, 11:45 AM CET