{"id":"https://openalex.org/W4406612934","doi":"https://doi.org/10.1109/smc54092.2024.10831538","title":"Hierarchical Policy Optimization for Cooperative Multi-Agent Reinforcement Learning","display_name":"Hierarchical Policy Optimization for Cooperative Multi-Agent Reinforcement Learning","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4406612934","doi":"https://doi.org/10.1109/smc54092.2024.10831538"},"language":"en","primary_location":{"id":"doi:10.1109/smc54092.2024.10831538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5049549826","display_name":"Sailing He","orcid":"https://orcid.org/0000-0002-3401-1125"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shunfan He","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048107920","display_name":"Ronghao Zheng","orcid":"https://orcid.org/0000-0002-9095-5905"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghao Zheng","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003643230","display_name":"Senlin Zhang","orcid":"https://orcid.org/0000-0001-5117-3110"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Senlin Zhang","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033808402","display_name":"Meiqin Liu","orcid":"https://orcid.org/0000-0003-0693-6574"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiqin Liu","raw_affiliation_strings":["Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049549826"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32307652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5087","last_page":"5092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.498199999332428,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.498199999332428,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8169654607772827},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6615874767303467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37916937470436096}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8169654607772827},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6615874767303467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37916937470436096}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc54092.2024.10831538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1502531386","display_name":null,"funder_award_id":"U23B2060,62173294","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4986667135","display_name":null,"funder_award_id":"LZ24F030001","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1918371733","https://openalex.org/W2124541940","https://openalex.org/W2145339207","https://openalex.org/W2149479912","https://openalex.org/W2617547828","https://openalex.org/W3113382536","https://openalex.org/W3129293693","https://openalex.org/W3163894240","https://openalex.org/W3213818741","https://openalex.org/W3217389438","https://openalex.org/W4221146329","https://openalex.org/W6684921986","https://openalex.org/W6738796088","https://openalex.org/W6749032143","https://openalex.org/W6749304979","https://openalex.org/W6754297394","https://openalex.org/W6756870468"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"To":[0],"handle":[1],"the":[2,5,8,36,93,110],"non-stationarity":[3],"of":[4,10,43,47,109],"environment":[6],"and":[7,100],"curse":[9],"dimensionality":[11],"issues":[12],"in":[13,103],"multi-agent":[14,63],"reinforcement":[15,64],"learning,":[16],"gathering":[17],"information":[18],"through":[19],"communication":[20,49,81,101],"is":[21,83,90,112],"a":[22,54],"critical":[23],"part.":[24],"Existing":[25],"frameworks":[26],"have":[27,41],"proposed":[28],"centralized":[29],"or":[30,45],"distributed":[31],"structures":[32],"to":[33,85],"deal":[34],"with":[35,75],"problem.":[37],"However,":[38],"they":[39],"either":[40],"problems":[42,46],"robustness":[44],"high":[48],"costs.":[50],"This":[51],"paper":[52],"adopts":[53],"hierarchical":[55,80],"zeroth-order":[56],"policy":[57],"optimization":[58],"(HZOPO)":[59],"algorithm":[60,95,111],"for":[61],"cooperative":[62,104],"learning":[65],"(MARL)":[66],"problems.":[67],"The":[68,107],"agents":[69],"are":[70],"divided":[71],"into":[72],"different":[73],"groups":[74],"high-and":[76],"low-level":[77],"entities.":[78],"A":[79],"structure":[82],"implemented":[84],"reach":[86],"global":[87],"consensus.":[88],"It":[89],"shown":[91],"that":[92],"HZOPO":[94],"can":[96],"balance":[97],"both":[98],"convergence":[99,108],"efficiency":[102],"MARL":[105],"environments.":[106],"also":[113],"proved.":[114]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}