{"id":"https://openalex.org/W4205331573","doi":"https://doi.org/10.1109/lra.2021.3135930","title":"Learning Cooperative Multi-Agent Policies With Partial Reward Decoupling","display_name":"Learning Cooperative Multi-Agent Policies With Partial Reward Decoupling","publication_year":2021,"publication_date":"2021-12-16","ids":{"openalex":"https://openalex.org/W4205331573","doi":"https://doi.org/10.1109/lra.2021.3135930"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3135930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3135930","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2112.12740","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081604594","display_name":"Benjamin Freed","orcid":"https://orcid.org/0000-0003-3741-3709"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Benjamin Freed","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3741-3709","affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023381180","display_name":"Aditya Kapoor","orcid":"https://orcid.org/0000-0002-2539-2675"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Kapoor","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062827877","display_name":"Ian Abraham","orcid":"https://orcid.org/0000-0003-0299-1760"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Abraham","raw_affiliation_strings":["Mechanical Engineering Department, Yale University, New Haven, CT, USA"],"raw_orcid":"https://orcid.org/0000-0003-0299-1760","affiliations":[{"raw_affiliation_string":"Mechanical Engineering Department, Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055199976","display_name":"Jeff Schneider","orcid":"https://orcid.org/0000-0002-5080-9073"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff Schneider","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5080-9073","affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048906141","display_name":"Howie Choset","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Howie Choset","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5434-7945","affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081604594"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71044922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"7","issue":"2","first_page":"890","last_page":"897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T11182","display_name":"Auction Theory and Applications","score":0.9703999757766724,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9531999826431274,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.7871002554893494},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47263047099113464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33514469861984253},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09115049242973328},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.08876264095306396}],"concepts":[{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.7871002554893494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47263047099113464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33514469861984253},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09115049242973328},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.08876264095306396}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2021.3135930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3135930","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2112.12740","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.12740","pdf_url":"https://arxiv.org/pdf/2112.12740","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2112.12740","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.12740","pdf_url":"https://arxiv.org/pdf/2112.12740","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1515851193","https://openalex.org/W1521003796","https://openalex.org/W1771410628","https://openalex.org/W1777239053","https://openalex.org/W2045031658","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2786303200","https://openalex.org/W2798705390","https://openalex.org/W2810602713","https://openalex.org/W2894976951","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3099518626","https://openalex.org/W3132143885","https://openalex.org/W3166401044","https://openalex.org/W4249736682","https://openalex.org/W4297733535","https://openalex.org/W4299802797","https://openalex.org/W4385245566","https://openalex.org/W6627932998","https://openalex.org/W6631137000","https://openalex.org/W6638018090","https://openalex.org/W6638088447","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6747993910","https://openalex.org/W6750645735","https://openalex.org/W6755069753","https://openalex.org/W6772005887"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4313561376","https://openalex.org/W3103825105","https://openalex.org/W3027880158","https://openalex.org/W3207533102","https://openalex.org/W1617565119","https://openalex.org/W160381218","https://openalex.org/W2512958550"],"abstract_inverted_index":{"One":[0],"of":[1,13,57,97,134],"the":[2,68],"preeminent":[3],"obstacles":[4],"to":[5,10,18,45,102,112,148],"scaling":[6],"multi-agent":[7,49,98,114],"reinforcement":[8],"learning":[9,88],"large":[11,47],"numbers":[12],"agents":[14],"is":[15],"assigning":[16],"credit":[17,28,61],"individual":[19],"agents\u2019":[20,137],"actions.":[21],"In":[22],"this":[23,27],"letter,":[24],"we":[25,35,108],"address":[26],"assignment":[29],"problem":[30,70],"with":[31],"an":[32,74],"approach":[33,111,127],"that":[34,66,125],"call":[36],"<italic":[37],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[38],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">partial":[39],"reward":[40,138],"decoupling</i>":[41],"(PRD),":[42],"which":[43,84],"attempts":[44],"decompose":[46],"cooperative":[48],"RL":[50,69,99],"problems":[51],"into":[52],"decoupled":[53],"subproblems":[54],"involving":[55],"subsets":[56],"agents,":[58],"thereby":[59],"simplifying":[60],"assignment.":[62],"We":[63],"empirically":[64,123],"demonstrate":[65],"decomposing":[67],"using":[71],"PRD":[72],"in":[73,78,136,145],"actor-critic":[75,105],"algorithm":[76],"results":[77],"lower":[79],"variance":[80],"policy":[81,115],"gradient":[82,116],"estimates,":[83],"improves":[85],"data":[86],"efficiency,":[87],"stability,":[89],"and":[90,122,140],"asymptotic":[91],"performance":[92],"across":[93],"a":[94,118],"wide":[95],"array":[96],"tasks,":[100],"compared":[101],"various":[103],"other":[104],"approaches.":[106],"Additionally,":[107],"relate":[109],"our":[110,126],"counterfactual":[113],"(COMA),":[117],"state-of-the-art":[119],"MARL":[120],"algorithm,":[121],"show":[124],"outperforms":[128],"COMA":[129],"by":[130,141],"making":[131],"better":[132],"use":[133],"information":[135],"streams,":[139],"enabling":[142],"recent":[143],"advances":[144],"advantage":[146],"estimation":[147],"be":[149],"used.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}