{"id":"https://openalex.org/W7123517001","doi":"https://doi.org/10.1145/3772052.3772227","title":"Multi-Agent Reinforcement Learning with Serverless Computing","display_name":"Multi-Agent Reinforcement Learning with Serverless Computing","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W7123517001","doi":"https://doi.org/10.1145/3772052.3772227"},"language":null,"primary_location":{"id":"doi:10.1145/3772052.3772227","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772052.3772227","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3772052.3772227","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122963612","display_name":"Rui Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rui Wei","raw_affiliation_strings":["Stevens Institute of Technology, Hoboken, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075787386","display_name":"Hanfei Yu","orcid":"https://orcid.org/0000-0001-5790-4981"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanfei Yu","raw_affiliation_strings":["Stevens Institute of Technology, Hoboken, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122990595","display_name":"Xikang Song","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xikang Song","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122939924","display_name":"Jian Li","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Li","raw_affiliation_strings":["Stony Brook University, Stony Brook, NY, USA"],"affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074406596","display_name":"Devesh Tiwari","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devesh Tiwari","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ying Mao","orcid":"https://orcid.org/0000-0002-4484-4892"},"institutions":[{"id":"https://openalex.org/I164389053","display_name":"Fordham University","ror":"https://ror.org/03qnxaf80","country_code":"US","type":"education","lineage":["https://openalex.org/I164389053"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Mao","raw_affiliation_strings":["Fordham University, New York, USA"],"affiliations":[{"raw_affiliation_string":"Fordham University, New York, USA","institution_ids":["https://openalex.org/I164389053"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065183586","display_name":"H Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Stevens Institute of Technology, Hoboken, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5122963612"],"corresponding_institution_ids":["https://openalex.org/I108468826"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82742471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.31470000743865967,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.31470000743865967,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.1665000021457672,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.04100000113248825,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8585000038146973},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5174999833106995},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.42170000076293945},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4196000099182129},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.36480000615119934},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3061000108718872}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8585000038146973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7080000042915344},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3946000039577484},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31700000166893005},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.2662000060081482}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3772052.3772227","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772052.3772227","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3772052.3772227","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772052.3772227","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7824450790","display_name":null,"funder_award_id":"2527416,2534241,2534286,2523997,2124897,2315614,2337914","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2099618002","https://openalex.org/W2560647685","https://openalex.org/W3118391542","https://openalex.org/W3132328326","https://openalex.org/W3138582970","https://openalex.org/W3184116135","https://openalex.org/W3207864249","https://openalex.org/W3210617645","https://openalex.org/W4214712602","https://openalex.org/W4220758675","https://openalex.org/W4285285554","https://openalex.org/W4306894812","https://openalex.org/W4327571609","https://openalex.org/W4401991666","https://openalex.org/W4405756449"],"related_works":[],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2],"(MARL)":[3],"has":[4,37],"emerged":[5],"as":[6,20,69],"a":[7],"promising":[8],"approach":[9],"for":[10,15,40],"tasks":[11],"requiring":[12],"multiple":[13],"agents":[14],"cooperation":[16],"or":[17],"competition,":[18],"such":[19],"scientific":[21],"simulation,":[22],"multi-robot":[23],"collaboration,":[24],"and":[25,33,44,64,73,80,86],"traffic":[26],"control.":[27],"Serverless":[28],"computing,":[29],"with":[30],"its":[31],"dynamic":[32,70],"flexible":[34],"resource":[35],"allocation,":[36],"demonstrated":[38],"potential":[39],"improving":[41],"training":[42,53],"efficiency":[43],"cost-efficiency":[45],"in":[46],"RL":[47,52],"workloads.":[48],"However,":[49],"existing":[50],"serverless":[51],"systems":[54],"focus":[55],"primarily":[56],"on":[57],"single-agent":[58],"scenarios,":[59],"overlooking":[60],"the":[61],"unique":[62],"characteristics":[63],"inherent":[65],"complexities":[66],"of":[67],"MARL\u2014such":[68],"inter-agent":[71],"relationships":[72],"heterogeneous":[74],"policy":[75],"requirements":[76],"across":[77],"agents\u2014leaving":[78],"inefficient":[79],"even":[81],"infeasible":[82],"support":[83],"to":[84],"diverse":[85],"complex":[87],"MARL":[88],"algorithms.":[89]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}
