Optimal Activation of Halting Multi-Armed Bandit Models

Cowan, Wesley, Katehakis, Michael N., Ross, Sheldon M.

arXiv.org Artificial Intelligence 

We study new types of dynamic allocation problems the {\sl Halting Bandit} models. As an application, we obtain new proofs for the classic Gittins index decomposition result and recent results of the authors in `Multi-armed bandits under general depreciation and commitment.'

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found