{"id":"https://openalex.org/W4385568329","doi":"https://doi.org/10.1145/3580305.3599379","title":"HiMacMic: Hierarchical Multi-Agent Deep Reinforcement Learning with Dynamic Asynchronous Macro Strategy","display_name":"HiMacMic: Hierarchical Multi-Agent Deep Reinforcement Learning with Dynamic Asynchronous Macro Strategy","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385568329","doi":"https://doi.org/10.1145/3580305.3599379"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599379","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5014609117","display_name":"Hancheng Zhang","orcid":"https://orcid.org/0009-0009-4479-5056"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hancheng Zhang","raw_affiliation_strings":["Beijing Inst. of Tech., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Inst. of Tech., Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102013272","display_name":"Guozheng Li","orcid":"https://orcid.org/0000-0001-6663-6712"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guozheng Li","raw_affiliation_strings":["Beijing Inst. of Tech., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Inst. of Tech., Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102923184","display_name":"Chi Harold Liu","orcid":"https://orcid.org/0000-0002-0252-329X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Harold Liu","raw_affiliation_strings":["Beijing Inst. of Tech., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Inst. of Tech., Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054991337","display_name":"Guoren Wang","orcid":"https://orcid.org/0000-0002-0181-8379"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoren Wang","raw_affiliation_strings":["Beijing Inst. of Tech., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Inst. of Tech., Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039176528","display_name":"Jian Tang","orcid":"https://orcid.org/0000-0003-4418-0114"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Tang","raw_affiliation_strings":["Midea Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Midea Group, Beijing, China","institution_ids":["https://openalex.org/I4210093653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014609117"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.174,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55377144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3239","last_page":"3248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9804999828338623,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8417729139328003},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.8395917415618896},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.814844012260437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8072695732116699},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.7150745391845703},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6009846925735474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5850467681884766},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43426400423049927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3621867895126343}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8417729139328003},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.8395917415618896},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.814844012260437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072695732116699},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.7150745391845703},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6009846925735474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5850467681884766},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43426400423049927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3621867895126343},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599379","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2600243670","display_name":null,"funder_award_id":"U21A20519","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3980498467","display_name":null,"funder_award_id":"61772072","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8565926968","display_name":null,"funder_award_id":"U21A2051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2292533394","https://openalex.org/W2773423866","https://openalex.org/W2886509985","https://openalex.org/W2925554975","https://openalex.org/W3156295478","https://openalex.org/W3166344325","https://openalex.org/W3205875899","https://openalex.org/W4281392159","https://openalex.org/W4290948528"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W2250140200","https://openalex.org/W3121791438"],"abstract_inverted_index":{"Multi-agent":[0],"deep":[1],"reinforcement":[2],"learning":[3],"(MADRL)":[4],"has":[5],"been":[6],"widely":[7,106],"used":[8,107],"in":[9,42,104],"many":[10],"scenarios":[11,47],"such":[12],"as":[13],"robotics":[14],"and":[15,54,95,113,127],"game":[16],"AI.":[17],"However,":[18],"existing":[19,133],"methods":[20],"mainly":[21],"focus":[22],"on":[23],"the":[24,32,49,88],"optimization":[25],"of":[26],"agents'":[27],"micro":[28],"policies":[29],"without":[30],"considering":[31],"macro":[33,73,89],"strategy.":[34,74],"As":[35],"a":[36,64,78,83],"result,":[37],"they":[38],"cannot":[39],"perform":[40],"well":[41],"complex":[43],"or":[44],"sparse":[45],"reward":[46],"like":[48],"StarCraft":[50],"Multi-Agent":[51],"Challenge":[52],"(SMAC)":[53],"Google":[55],"Research":[56],"Football":[57],"(GRF).":[58],"To":[59],"this":[60],"end,":[61],"we":[62],"propose":[63],"hierarchical":[65],"MADRL":[66],"framework":[67],"called":[68],"\"HiMacMic\"":[69],"with":[70,115],"dynamic":[71],"asynchronous":[72],"Spatially,":[75],"HiMacMic":[76,103,122],"determines":[77],"critical":[79],"position":[80],"by":[81],"using":[82],"positional":[84],"heat":[85],"map.":[86],"Temporally,":[87],"strategy":[90],"dynamically":[91],"decides":[92],"its":[93,138],"deadline":[94],"updates":[96],"it":[97],"asynchronously":[98],"among":[99],"agents.":[100],"We":[101],"validate":[102],"four":[105],"benchmarks,":[108],"namely:":[109],"Overcooked,":[110],"GRF,":[111],"SMAC":[112],"SMAC-v2":[114],"nine":[116],"chosen":[117],"scenarios.":[118],"Results":[119],"show":[120],"that":[121],"not":[123],"only":[124],"converges":[125],"faster":[126],"achieves":[128],"higher":[129],"results":[130],"than":[131],"ten":[132],"approaches,":[134],"but":[135],"also":[136],"shows":[137],"adaptability":[139],"to":[140],"different":[141],"environment":[142],"settings.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}