A cluster-aware multi-agent bandit algorithm achieves O((C/M) log T) regret by aggregating information within clusters and communicating only between clusters, improving on the O(M^2 log T) bound of fully heterogeneous prior work.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Heterogeneous Multi-agent Multi-armed Bandits on Stochastic Block Models
A cluster-aware multi-agent bandit algorithm achieves O((C/M) log T) regret by aggregating information within clusters and communicating only between clusters, improving on the O(M^2 log T) bound of fully heterogeneous prior work.