Search Results for author:
Found 2 papers, 0 papers with code
Dynamic Spectrum Access using Stochastic Multi-User Bandits
In contrast to prior work, it is assumed that rewards can be non-zero even under collisions, thus allowing for the number of users to be greater than the number of channels.
Multi-User Multi-Armed Bandits for Uncoordinated Spectrum Access
The algorithms in both stochastic and adversarial scenarios are extended to the dynamic case where the number of users in the system evolves over time and are shown to lead to sub-linear regret.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
