{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/150295"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/150295","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Efficient Decentralized Multi-Agent Learning in Asymmetric Bipartite Queuing Systems","abstract":"We study decentralized multi-agent learning in bipartite queuing systems, a standard model for service systems. In particular, 𝑁 agents request service from 𝐾 servers in a fully decentralized way, i.e, by running the same algorithm without communication. Previous decentralized algorithms are restricted to symmetric systems, have performance that is degrading exponentially in the number of servers, require communication through shared randomness and unique agent identities, and are computationally demanding. In contrast, we provide a simple learning algorithm that, when run decentrally by each agent, leads the queuing system to have efficient performance in general asymmetric bipartite queuing systems while also having additional robustness properties. Along the way, we provide the first provably efficient UCB-based algorithm for the centralized case of the problem.","abstract_html":"We study decentralized multi-agent learning in bipartite queuing systems, a standard model for service systems. In particular, 𝑁 agents request service from 𝐾 servers in a fully decentralized way, i.e, by running the same algorithm without communication. Previous decentralized algorithms are restricted to symmetric systems, have performance that is degrading exponentially in the number of servers, require communication through shared randomness and unique agent identities, and are computationally demanding. In contrast, we provide a simple learning algorithm that, when run decentrally by each agent, leads the queuing system to have efficient performance in general asymmetric bipartite queuing systems while also having additional robustness properties. Along the way, we provide the first provably efficient UCB-based algorithm for the centralized case of the problem.","abstract_has_math":false,"creators":["Weng, Wentao"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Freund, Daniel","Lykouris, Thodoris"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-02","date_published":"2023-02","updated_at":"2026-07-22T22:21:17Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/150295","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Freund, Daniel","Lykouris, Thodoris"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Weng, Wentao"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-03-31T14:45:47Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-03-31T14:45:47Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-02"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Science in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/150295"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["We study decentralized multi-agent learning in bipartite queuing systems, a standard model for service systems. In particular, 𝑁 agents request service from 𝐾 servers in a fully decentralized way, i.e, by running the same algorithm without communication. Previous decentralized algorithms are restricted to symmetric systems, have performance that is degrading exponentially in the number of servers, require communication through shared randomness and unique agent identities, and are computationally demanding. In contrast, we provide a simple learning algorithm that, when run decentrally by each agent, leads the queuing system to have efficient performance in general asymmetric bipartite queuing systems while also having additional robustness properties. Along the way, we provide the first provably efficient UCB-based algorithm for the centralized case of the problem."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Efficient Decentralized Multi-Agent Learning in Asymmetric Bipartite Queuing Systems"]}]}],"canonical_facts":{"dc:contributor.advisor":["Freund, Daniel","Lykouris, Thodoris"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Weng, Wentao"],"dc:date.accessioned":["2023-03-31T14:45:47Z"],"dc:date.available":["2023-03-31T14:45:47Z"],"dc:date.issued":["2023-02"],"dc:description.abstract":["We study decentralized multi-agent learning in bipartite queuing systems, a standard model for service systems. In particular, 𝑁 agents request service from 𝐾 servers in a fully decentralized way, i.e, by running the same algorithm without communication. Previous decentralized algorithms are restricted to symmetric systems, have performance that is degrading exponentially in the number of servers, require communication through shared randomness and unique agent identities, and are computationally demanding. In contrast, we provide a simple learning algorithm that, when run decentrally by each agent, leads the queuing system to have efficient performance in general asymmetric bipartite queuing systems while also having additional robustness properties. Along the way, we provide the first provably efficient UCB-based algorithm for the centralized case of the problem."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/150295"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Efficient Decentralized Multi-Agent Learning in Asymmetric Bipartite Queuing Systems"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Science in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:17Z"}