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

Udari Madhushani, Naomi Ehrich Leonard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

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. 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.

Original languageEnglish (US)
Title of host publication2019 18th European Control Conference, ECC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3502-3507
Number of pages6
ISBN (Electronic)9783907144008
DOIs
StatePublished - Jun 2019
Event18th European Control Conference, ECC 2019 - Naples, Italy
Duration: Jun 25 2019Jun 28 2019

Publication series

Name2019 18th European Control Conference, ECC 2019

Conference

Conference18th European Control Conference, ECC 2019
CountryItaly
CityNaples
Period6/25/196/28/19

All Science Journal Classification (ASJC) codes

  • Instrumentation
  • Control and Optimization

Fingerprint Dive into the research topics of 'Heterogeneous stochastic interactions for multiple agents in a multi-armed bandit problem'. Together they form a unique fingerprint.

Cite this