@inproceedings{cdde4aff735f45d1afbe88d7d1889b78,

title = "A Dynamic Observation Strategy for Multi-agent Multi-armed Bandit Problem",

abstract = "We define and analyze a multi-agent multi-armed bandit problem in which decision-making agents can observe the choices and rewards of their neighbors under a linear observation cost. Neighbors are defined by a network graph that encodes the inherent observation constraints of the system. We define a cost associated with observations such that at every instance an agent makes an observation it receives a constant observation regret. We design a sampling algorithm and an observation protocol for each agent to maximize its own expected cumulative reward through minimizing expected cumulative sampling regret and expected cumulative observation regret. For our proposed protocol, we prove that total cumulative regret is logarithmically bounded. We verify the accuracy of analytical bounds using numerical simulations.",

author = "Udari Madhushani and Leonard, {Naomi Ehrich}",

note = "Publisher Copyright: {\textcopyright} 2020 EUCA.; 18th European Control Conference, ECC 2020 ; Conference date: 12-05-2020 Through 15-05-2020",

year = "2020",

month = may,

language = "English (US)",

series = "European Control Conference 2020, ECC 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1677--1682",

booktitle = "European Control Conference 2020, ECC 2020",

address = "United States",

}