Recurrent Submodular Welfare and Matroid Blocking Semi-Bandits

Neural Information Processing Systems 

In this work, we extend the above direction to a combinatorial semi-bandit setting and study a variant of stochastic MAB, where arms are subject to matroid constraints and each arm becomes unavailable (blocked) for a fixed number of rounds after each play.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found