Abstract
We provide a short and elementary proof of the Gittins index theorem for the multi-armed bandit problem, for the case where each bandit is modeled as a finite-state semi-Markov process. We also indicate how this proof can be extended to the branching bandits and Klimov problems.
Citation
John N. Tsitsiklis. "A Short Proof of the Gittins Index Theorem." Ann. Appl. Probab. 4 (1) 194 - 199, February, 1994. https://doi.org/10.1214/aoap/1177005207
Information
