On Regret-optimal Cooperative Nonstochastic Multi-armed Bandits

11/30/2022
by   Jialin Yi, et al.
0

We consider the nonstochastic multi-agent multi-armed bandit problem with agents collaborating via a communication network with delays. We show a lower bound for individual regret of all agents. We show that with suitable regularizers and communication protocols, a collaborative multi-agent follow-the-regularized-leader (FTRL) algorithm has an individual regret upper bound that matches the lower bound up to a constant factor when the number of arms is large enough relative to degrees of agents in the communication graph. We also show that an FTRL algorithm with a suitable regularizer is regret optimal with respect to the scaling with the edge-delay parameter. We present numerical experiments validating our theoretical results and demonstrate cases when our algorithms outperform previously proposed algorithms.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset