Optimal Activation of Halting Multi-Armed Bandit Models
arXiv:2304.10302v11 citationsh-index: 40
Originality Synthesis-oriented
AI Analysis
This is an incremental contribution to theoretical multi-armed bandit research, offering alternative proofs for existing results.
The paper tackles dynamic allocation problems in Halting Bandit models, providing new proofs for the classic Gittins index decomposition and recent results from prior work.
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.'