Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams

Erdem Býyýk, Anusha Lalitha, Rajarshi Saha, Andrea Goldsmith, Dorsa Sadigh

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

1 Scopus citations

Abstract

When humans collaborate with each other, they often make decisions by observing others and considering the consequences that their actions may have on the entire team, instead of greedily doing what is best for just themselves. We would like our AI agents to effectively collaborate in a similar way by capturing a model of their partners. In this work, we propose and analyze a decentralized Multi-Armed Bandit (MAB) problem with coupled rewards as an abstraction of more general multi-agent collaboration. We demonstrate that näýve extensions of single-agent optimal MAB algorithms fail when applied for decentralized bandit teams. Instead, we propose a Partner-Aware strategy for joint sequential decision-making that extends the well-known single-agent Upper Confidence Bound algorithm. We analytically show that our proposed strategy achieves logarithmic regret, and provide extensive experiments involving human-AI and human-robot collaboration to validate our theoretical findings. Our results show that the proposed partner-aware strategy outperforms other known methods, and our human subject studies suggest humans prefer to collaborate with AI agents implementing our partner-aware strategy.

Original languageEnglish (US)
Title of host publicationAAAI-22 Technical Tracks 9
PublisherAssociation for the Advancement of Artificial Intelligence
Pages9296-9303
Number of pages8
ISBN (Electronic)1577358767, 9781577358763
DOIs
StatePublished - Jun 30 2022
Event36th AAAI Conference on Artificial Intelligence, AAAI 2022 - Virtual, Online
Duration: Feb 22 2022Mar 1 2022

Publication series

NameProceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
Volume36

Conference

Conference36th AAAI Conference on Artificial Intelligence, AAAI 2022
CityVirtual, Online
Period2/22/223/1/22

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams'. Together they form a unique fingerprint.

Cite this