乐胖代购免代理版

{"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":{"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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://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":false,"raw_author_name":"Benjamin Freed","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"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"],"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"],"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"],"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"],"affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.342,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":3,"citation_normalized_percentile":{"value":0.634001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":72,"max":76},"biblio":{"volume":"7","issue":"2","first_page":"890","last_page":"897"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991,"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":0.9991,"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":0.9704,"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":0.9532,"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":0.78710026}],"concepts":[{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.78710026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47263047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3351447},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09115049},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.08876264}],"mesh":[],"locations_count":4,"locations":[{"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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.12740","pdf_url":"http://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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2112.12740","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.12740","pdf_url":"http://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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":["https://openalex.org/W4205331573"],"referenced_works_count":24,"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"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W4313561376","https://openalex.org/W3207533102","https://openalex.org/W3103825105","https://openalex.org/W3027880158","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2512958550","https://openalex.org/W1617565119","https://openalex.org/W160381218"],"abstract_inverted_index":{"One":[0],"of":[1,13,55,95,132],"the":[2,66],"preeminent":[3],"obstacles":[4],"to":[5,10,18,43,100,110,146],"scaling":[6],"multi-agent":[7,47,96,112],"reinforcement":[8],"learning":[9,86],"large":[11,45],"numbers":[12],"agents":[14],"is":[15],"assigning":[16],"credit":[17,28,59],"individual":[19],"agents'":[20,135],"actions.":[21],"In":[22],"this":[23,27],"paper,":[24],"we":[25,35,106],"address":[26],"assignment":[29],"problem":[30,68],"with":[31],"an":[32,72],"approach":[33,109,125],"that":[34,64,123],"call":[36],"\\textit{partial":[37],"reward":[38,136],"decoupling}":[39],"(PRD),":[40],"which":[41,82],"attempts":[42],"decompose":[44],"cooperative":[46],"RL":[48,67,97],"problems":[49],"into":[50],"decoupled":[51],"subproblems":[52],"involving":[53],"subsets":[54],"agents,":[56],"thereby":[57],"simplifying":[58],"assignment.":[60],"We":[61],"empirically":[62,121],"demonstrate":[63],"decomposing":[65],"using":[69],"PRD":[70],"in":[71,76,134,143],"actor-critic":[73,103],"algorithm":[74],"results":[75],"lower":[77],"variance":[78],"policy":[79,113],"gradient":[80,114],"estimates,":[81],"improves":[83],"data":[84],"efficiency,":[85],"stability,":[87],"and":[88,120,138],"asymptotic":[89],"performance":[90],"across":[91],"a":[92,116],"wide":[93],"array":[94],"tasks,":[98],"compared":[99],"various":[101],"other":[102],"approaches.":[104],"Additionally,":[105],"relate":[107],"our":[108,124],"counterfactual":[111],"(COMA),":[115],"state-of-the-art":[117],"MARL":[118],"algorithm,":[119],"show":[122],"outperforms":[126],"COMA":[127],"by":[128,139],"making":[129],"better":[130],"use":[131],"information":[133],"streams,":[137],"enabling":[140],"recent":[141],"advances":[142],"advantage":[144],"estimation":[145],"be":[147],"used.":[148]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4205331573","counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2024-12-24T05:18:10.183478","created_date":"2022-01-26"}