Four proofs of Gittins’ multiarmed bandit theorem

Bandit Processes and Dynamic Allocation Indices

John Gittins · Journal of the Royal Statistical Society Series B (Statistical Methodology) · 1979 · 1.5K citations

Mathematical Programming, Dynamic Allocation Indices, Engineering +11

Introduction to Stochastic Dynamic Programming.

Donald A. Berry, Sheldon M. Ross · Journal of the American Statistical Association · 1986 · 1.2K citations

Stochastic Simulation, Engineering, Stochastic Processes +6

Restless bandits: activity allocation in a changing world

Peter Whittle · Journal of Applied Probability · 1988 · 1.1K citations

Mathematical Programming, Engineering, Project Scheduling +21

Semi-Infinite Programming: Theory, Methods, and Applications

R. Hettich, K. O. Kortanek · SIAM Review · 1993 · 1K citations

Mathematical Programming, Numerical Analysis, Semi-infinite Programming +15

Multi-Armed Bandits and the Gittins Index

Peter Whittle · Journal of the Royal Statistical Society Series B (Statistical Methodology) · 1980 · 526 citations

Engineering, Game Theory, Operations Research +16