Stationary multi-choice bandit problems.

DOI10.1016/S0165-1889(99)00064-0zbMath1056.90076MaRDI QIDQ5958100

Dirk Bergemann, Juuso Välimäki

Publication date: 3 March 2002

Published in: Journal of Economic Dynamics \& Control (Search for Journal in Brave)

Mathematics Subject Classification ID

Stochastic scheduling theory in operations research (90B36)

Related Items (20)

Hierarchical experimentation ⋮ Keeping your options open ⋮ Robustness of stochastic bandit policies ⋮ Common value experimentation ⋮ A central limit theorem, loss aversion and multi-armed bandits ⋮ Strategic experimentation with private payoffs ⋮ Competitive problem solving and the optimal prize schemes ⋮ Large firms and within firm occupational reallocation ⋮ On games of strategic experimentation ⋮ Strategic information exchange ⋮ Strategic learning in teams ⋮ Decomposing risk in an exploitation-exploration problem with endogenous termination time ⋮ Undiscounted bandit games ⋮ Branching bandits: A sequential search process with correlated pay-offs. ⋮ Learning from failures: optimal contracts for experimentation and production ⋮ Cooperation dynamics in repeated games of adverse selection ⋮ Optimal search from multiple distributions with infinite horizon ⋮ Response adaptive designs that incorporate switching costs and constraints ⋮ Inefficiency of sponsored research ⋮ Two-Armed Restless Bandits with Imperfect Information: Stochastic Control and Indexability

Cites Work

• Unnamed Item
• Unnamed Item
• Extensions of the multiarmed bandit problem: The discounted case
• Optimal Search for the Best Alternative
• Denumerable-Armed Bandits
• Switching Costs and the Gittins Index

This page was built for publication: Stationary multi-choice bandit problems.