Skip to main content

Heterogeneous stochastic interactions for multiple agents in a multi-armed bandit problem

Author(s): Madhushani, U; Leonard, Naomi E

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr10w10
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMadhushani, U-
dc.contributor.authorLeonard, Naomi E-
dc.date.accessioned2021-10-08T20:20:03Z-
dc.date.available2021-10-08T20:20:03Z-
dc.date.issued2019en_US
dc.identifier.citationMadhushani, U, Leonard, NE. (2019). Heterogeneous stochastic interactions for multiple agents in a multi-armed bandit problem. 3502 - 3507. doi:10.23919/ECC.2019.8796036en_US
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr10w10-
dc.description.abstractWe define and analyze a multi-agent multi-armed bandit problem in which decision-making agents can observe the choices and rewards of their neighbors. Neighbors are defined by a network graph with heterogeneous and stochastic interconnections. These interactions are determined by the sociability of each agent, which corresponds to the probability that the agent observes its neighbors. We design an algorithm for each agent to maximize its own expected cumulative reward and prove performance bounds that depend on the sociability of the agents and the network structure. We use the bounds to predict the rank ordering of agents according to their performance and verify the accuracy analytically and computationally.en_US
dc.format.extent3502 - 3507en_US
dc.language.isoen_USen_US
dc.relation.ispartof2019 18th European Control Conferenceen_US
dc.rightsAuthor's manuscripten_US
dc.titleHeterogeneous stochastic interactions for multiple agents in a multi-armed bandit problemen_US
dc.typeConference Articleen_US
dc.identifier.doidoi:10.23919/ECC.2019.8796036-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
Heterogeneous stochastic interactions for multiple agents in a multi-armed bandit problem.pdf493.95 kBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.