Optimal Activation of Halting Multi-Armed Bandit Models

04/20/2023

∙

We study new types of dynamic allocation problems the 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.'

READ FULL TEXT

Optimal Activation of Halting Multi-Armed Bandit Models

Online Multi-Armed Bandit

PAC-Bayesian Lifelong Learning For Multi-Armed Bandits

Practical Calculation of Gittins Indices for Multi-armed Bandits

Using Subjective Logic to Estimate Uncertainty in Multi-Armed Bandit Problems

Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering

Sustainable Cooperative Coevolution with a Multi-Armed Bandit

A Central Limit Theorem, Loss Aversion and Multi-Armed Bandits

Optimal Activation of Halting Multi-Armed Bandit Models

Related Research

Online Multi-Armed Bandit

PAC-Bayesian Lifelong Learning For Multi-Armed Bandits

Practical Calculation of Gittins Indices for Multi-armed Bandits

Using Subjective Logic to Estimate Uncertainty in Multi-Armed Bandit Problems

Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering

Sustainable Cooperative Coevolution with a Multi-Armed Bandit

A Central Limit Theorem, Loss Aversion and Multi-Armed Bandits