Show simple item record

dc.contributor.authorWu, Sarah A
dc.contributor.authorWang, Rose E
dc.contributor.authorEvans, James A
dc.contributor.authorTenenbaum, Joshua B
dc.contributor.authorParkes, David C
dc.contributor.authorKleiman-Weiner, Max
dc.date.accessioned2021-12-08T15:38:12Z
dc.date.available2021-12-08T15:38:12Z
dc.date.issued2021
dc.identifier.urihttps://hdl.handle.net/1721.1/138376
dc.description.abstractCollaboration requires agents to coordinate their behavior on the fly, sometimes cooperating to solve a single task together and other times dividing it up into sub-tasks to work on in parallel. Underlying the human ability to collaborate is theory-of-mind (ToM), the ability to infer the hidden mental states that drive others to act. Here, we develop Bayesian Delegation, a decentralized multi-agent learning mechanism with these abilities. Bayesian Delegation enables agents to rapidly infer the hidden intentions of others by inverse planning. We test Bayesian Delegation in a suite of multi-agent Markov decision processes inspired by cooking problems. On these tasks, agents with Bayesian Delegation coordinate both their high-level plans (e.g., what sub-task they should work on) and their low-level actions (e.g., avoiding getting in each other's way). When matched with partners that act using the same algorithm, Bayesian Delegation outperforms alternatives. Bayesian Delegation is also a capable ad hoc collaborator and successfully coordinates with other agent types even in the absence of prior experience. Finally, in a behavioral experiment, we show that Bayesian Delegation makes inferences similar to human observers about the intent of others. Together, these results argue for the centrality of ToM for successful decentralized multi-agent collaboration.en_US
dc.language.isoen
dc.publisherWileyen_US
dc.relation.isversionof10.1111/TOPS.12525en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourcearXiven_US
dc.titleToo Many Cooks: Bayesian Inference for Coordinating Multi‐Agent Collaborationen_US
dc.typeArticleen_US
dc.identifier.citationWu, Sarah A, Wang, Rose E, Evans, James A, Tenenbaum, Joshua B, Parkes, David C et al. 2021. "Too Many Cooks: Bayesian Inference for Coordinating Multi‐Agent Collaboration." Topics in Cognitive Science, 13 (2).
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
dc.contributor.departmentMassachusetts Institute of Technology. Department of Brain and Cognitive Sciences
dc.contributor.departmentCenter for Brains, Minds, and Machines
dc.relation.journalTopics in Cognitive Scienceen_US
dc.eprint.versionOriginal manuscripten_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2021-12-08T15:35:13Z
dspace.orderedauthorsWu, SA; Wang, RE; Evans, JA; Tenenbaum, JB; Parkes, DC; Kleiman-Weiner, Men_US
dspace.date.submission2021-12-08T15:35:15Z
mit.journal.volume13en_US
mit.journal.issue2en_US
mit.licenseOPEN_ACCESS_POLICY
mit.metadata.statusAuthority Work and Publication Information Neededen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record