TY - JOUR

T1 - Individual regret in cooperative nonstochastic multi-armed bandits

AU - Bar-On, Yogev

AU - Mansour, Yishay

N1 - Publisher Copyright:
© 2019 Neural information processing systems foundation. All rights reserved.

PY - 2019

Y1 - 2019

N2 - We study agents communicating over an underlying network by exchanging messages, in order to optimize their individual regret in a common nonstochastic multi-armed bandit problem. We derive regret minimization algorithms that guarantee for each agent v an individual expected regret of Oe (r( 1 + |NK(v)| ) T ), where T is the number of time steps, K is the number of actions and N (v) is the set of neighbors of agent v in the communication graph. We present algorithms both for the case that the communication graph is known to all the agents, and for the case that the graph is unknown. When the graph is unknown, each agent knows only the set of its neighbors and an upper bound on the total number of agents. The individual regret between the models differs only by a logarithmic factor. Our work resolves an open problem from [Cesa-Bianchi et al., 2019b].

AB - We study agents communicating over an underlying network by exchanging messages, in order to optimize their individual regret in a common nonstochastic multi-armed bandit problem. We derive regret minimization algorithms that guarantee for each agent v an individual expected regret of Oe (r( 1 + |NK(v)| ) T ), where T is the number of time steps, K is the number of actions and N (v) is the set of neighbors of agent v in the communication graph. We present algorithms both for the case that the communication graph is known to all the agents, and for the case that the graph is unknown. When the graph is unknown, each agent knows only the set of its neighbors and an upper bound on the total number of agents. The individual regret between the models differs only by a logarithmic factor. Our work resolves an open problem from [Cesa-Bianchi et al., 2019b].

UR - http://www.scopus.com/inward/record.url?scp=85084581915&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???

AN - SCOPUS:85084581915

SN - 1049-5258

VL - 32

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

T2 - 33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019

Y2 - 8 December 2019 through 14 December 2019

ER -