Timezone: »

Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits
Ronshee Chawla · Daniel Vial · Sanjay Shakkottai · R Srikant

Tue Jul 25 02:00 PM -- 04:30 PM (PDT) @ Exhibit Hall 1 #743
The study of collaborative multi-agent bandits has attracted significant attention recently. In light of this, we initiate the study of a new collaborative setting, consisting of $N$ agents such that each agent is learning one of $M$ stochastic multi-armed bandits to minimize their group cumulative regret. We develop decentralized algorithms which facilitate collaboration between the agents under two scenarios. We characterize the performance of these algorithms by deriving the per agent cumulative regret and group regret upper bounds. We also prove lower bounds for the group regret in this setting, which demonstrates the near-optimal behavior of the proposed algorithms.

Author Information

Ronshee Chawla (University of Texas at Austin)
Daniel Vial (UT Austin / UIUC)
Sanjay Shakkottai (University of Texas at Austin)
R Srikant (UIUC)

More from the Same Authors