{"id":"https://openalex.org/W4375869261","doi":"https://doi.org/10.1109/icassp49357.2023.10095374","title":"Hierarchical Multi-Agent Reinforcement Learning with Intrinsic Reward Rectification","display_name":"Hierarchical Multi-Agent Reinforcement Learning with Intrinsic Reward Rectification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869261","doi":"https://doi.org/10.1109/icassp49357.2023.10095374"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040374470","display_name":"Zhihao Liu","orcid":"https://orcid.org/0000-0003-1099-5745"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210125919","display_name":"Fusion (United States)","ror":"https://ror.org/02vtgg877","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125919"]},{"id":"https://openalex.org/I4210149442","display_name":"Fusion Academy","ror":"https://ror.org/05rwjyj14","country_code":"US","type":"education","lineage":["https://openalex.org/I4210149442"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhihao Liu","raw_affiliation_strings":["Chinese Academy of Sciences,Fusion Innovation Center, Institute of Automation","Fusion Innovation Center, Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Fusion Innovation Center, Institute of Automation","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Fusion Innovation Center, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210149442","https://openalex.org/I19820366","https://openalex.org/I4210125919"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628168","display_name":"Zhiwei Xu","orcid":"https://orcid.org/0000-0002-0754-5295"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210125919","display_name":"Fusion (United States)","ror":"https://ror.org/02vtgg877","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125919"]},{"id":"https://openalex.org/I4210149442","display_name":"Fusion Academy","ror":"https://ror.org/05rwjyj14","country_code":"US","type":"education","lineage":["https://openalex.org/I4210149442"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhiwei Xu","raw_affiliation_strings":["Chinese Academy of Sciences,Fusion Innovation Center, Institute of Automation","School of Artificial Intelligence, University of Chinese Academy of Sciences","Fusion Innovation Center, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Fusion Innovation Center, Institute of Automation","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Fusion Innovation Center, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210149442","https://openalex.org/I19820366","https://openalex.org/I4210125919"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101572310","display_name":"Guoliang Fan","orcid":"https://orcid.org/0000-0003-2724-2432"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210125919","display_name":"Fusion (United States)","ror":"https://ror.org/02vtgg877","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125919"]},{"id":"https://openalex.org/I4210149442","display_name":"Fusion Academy","ror":"https://ror.org/05rwjyj14","country_code":"US","type":"education","lineage":["https://openalex.org/I4210149442"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Guoliang Fan","raw_affiliation_strings":["Chinese Academy of Sciences,Fusion Innovation Center, Institute of Automation","Fusion Innovation Center, Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Fusion Innovation Center, Institute of Automation","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Fusion Innovation Center, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210149442","https://openalex.org/I19820366","https://openalex.org/I4210125919"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7739652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9616000056266785,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9609000086784363,"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":0.8938205242156982},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.8005151152610779},{"id":"https://openalex.org/keywords/rectification","display_name":"Rectification","score":0.680148720741272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6731001734733582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5700716972351074},{"id":"https://openalex.org/keywords/intrinsic-motivation","display_name":"Intrinsic motivation","score":0.5444120764732361},{"id":"https://openalex.org/keywords/intrinsic-value","display_name":"Intrinsic value (animal ethics)","score":0.5138152241706848},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5046519041061401},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45931628346443176},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4318923354148865},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.42320287227630615},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15002480149269104},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09359294176101685}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8938205242156982},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.8005151152610779},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.680148720741272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6731001734733582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5700716972351074},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.5444120764732361},{"id":"https://openalex.org/C195711298","wikidata":"https://www.wikidata.org/wiki/Q6058737","display_name":"Intrinsic value (animal ethics)","level":2,"score":0.5138152241706848},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5046519041061401},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45931628346443176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4318923354148865},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42320287227630615},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15002480149269104},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09359294176101685},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C95124753","wikidata":"https://www.wikidata.org/wiki/Q875686","display_name":"Environmental ethics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1639167632","https://openalex.org/W1924770834","https://openalex.org/W2012812921","https://openalex.org/W2166533447","https://openalex.org/W2539402368","https://openalex.org/W2626637010","https://openalex.org/W2747213132","https://openalex.org/W2892515961","https://openalex.org/W2962686687","https://openalex.org/W2963262099","https://openalex.org/W2964227312","https://openalex.org/W2965908679","https://openalex.org/W3089778445","https://openalex.org/W4287755265","https://openalex.org/W4288091739","https://openalex.org/W4288594419","https://openalex.org/W4382202831","https://openalex.org/W6640212811","https://openalex.org/W6703271639","https://openalex.org/W6734215269","https://openalex.org/W6739516088","https://openalex.org/W6749304979","https://openalex.org/W6758714175","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6767327128","https://openalex.org/W6771235960","https://openalex.org/W6783196708","https://openalex.org/W6784152626"],"related_works":["https://openalex.org/W4286620790","https://openalex.org/W2504683458","https://openalex.org/W4317808552","https://openalex.org/W1639186205","https://openalex.org/W2016549368","https://openalex.org/W3125158857","https://openalex.org/W4388047213","https://openalex.org/W2079413293","https://openalex.org/W2973135269","https://openalex.org/W2761784209"],"abstract_inverted_index":{"Hierarchical":[0],"reinforcement":[1,90],"learning":[2,91],"(HRL)":[3],"is":[4,53],"a":[5,84],"promising":[6],"approach":[7],"to":[8,50,63],"solving":[9],"long-term":[10],"decision":[11],"problems":[12],"and":[13,30,105],"complex":[14],"tasks,":[15],"as":[16],"high-level":[17],"policy":[18,26,66],"can":[19,98],"guide":[20],"the":[21,34,100,107,118,124],"training":[22],"procedure":[23],"of":[24,102],"low-level":[25,51,65],"with":[27,67,93],"macro":[28,37,72,103],"actions":[29,38,73,104],"intrinsic":[31,69,94,108],"rewards.":[32,109],"However,":[33],"amount":[35],"that":[36,112],"influence":[39],"decision-making,":[40],"which":[41,97],"affects":[42],"how":[43],"much":[44],"internal":[45],"rewards":[46,70],"should":[47],"be":[48,61],"given":[49],"policy,":[52],"disregarded":[54],"by":[55],"current":[56],"HRL":[57],"algorithms.":[58],"It":[59],"may":[60],"reasonable":[62],"provide":[64],"less":[68,75],"if":[71],"are":[74],"important":[76],"in":[77],"decision-making.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82],"propose":[83],"value":[85,120],"decomposition":[86,121],"based":[87],"hierarchical":[88],"multi-agent":[89],"method":[92,115],"reward":[95],"rectification,":[96],"determine":[99],"effectiveness":[101],"correct":[106],"We":[110],"show":[111],"our":[113],"proposed":[114],"significantly":[116],"outperforms":[117],"state-of-the-art":[119],"approaches":[122],"on":[123],"StarCraft":[125],"Multi-Agent":[126],"Challenge":[127],"platform.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}