About this document
Fair Combinatorial Multi-Armed Bandits by Urwa Malik is a document available to read on EtoBox.
This paper addresses the combinatorial multi-armed bandit (MAB) problem with fairness constraints, proposing a new selection algorithm that achieves a sublinear regret bound of O(T ln T) while maximizing total rewards. The authors integrate online convex optimization techniques to handle complex objectives and constraints, extending the model to include knapsack constraints. Extensive simulations demonstrate the algorithm
- Author
- Urwa Malik
- Language
- EN