{"id":"https://openalex.org/W4387740163","doi":"https://doi.org/10.1007/s40747-023-01255-5","title":"A hierarchical multi-agent allocation-action learning framework for multi-subtask games","display_name":"A hierarchical multi-agent allocation-action learning framework for multi-subtask games","publication_year":2023,"publication_date":"2023-10-18","ids":{"openalex":"https://openalex.org/W4387740163","doi":"https://doi.org/10.1007/s40747-023-01255-5"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-023-01255-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-023-01255-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01255-5.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01255-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100660420","display_name":"Xianglong Li","orcid":"https://orcid.org/0009-0005-2805-8970"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xianglong Li","raw_affiliation_strings":["Academy of Military Sciences, Beijing, 100091, China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Sciences, Beijing, 100091, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716337","display_name":"Yuan Li","orcid":"https://orcid.org/0000-0002-6245-9437"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":["Academy of Military Sciences, Beijing, 100091, China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Sciences, Beijing, 100091, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101741623","display_name":"Jieyuan Zhang","orcid":"https://orcid.org/0000-0003-2100-1312"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jieyuan Zhang","raw_affiliation_strings":["Academy of Military Sciences, Beijing, 100091, China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Sciences, Beijing, 100091, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101775095","display_name":"Xinhai Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinhai Xu","raw_affiliation_strings":["Academy of Military Sciences, Beijing, 100091, China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Sciences, Beijing, 100091, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102012605","display_name":"Donghong Liu","orcid":"https://orcid.org/0000-0001-7529-2253"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donghong Liu","raw_affiliation_strings":["Academy of Military Sciences, Beijing, 100091, China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Sciences, Beijing, 100091, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100660420"],"corresponding_institution_ids":[],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":1.3704,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85075915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"10","issue":"2","first_page":"1985","last_page":"1995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9696000218391418,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9488999843597412,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8261886835098267},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7765747308731079},{"id":"https://openalex.org/keywords/premise","display_name":"Premise","score":0.6188963055610657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6050180792808533},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5821110606193542},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.505872905254364},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49037742614746094},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.45313990116119385},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41882646083831787},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4178091287612915},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37337857484817505},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1047106385231018}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8261886835098267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7765747308731079},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.6188963055610657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050180792808533},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5821110606193542},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.505872905254364},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49037742614746094},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.45313990116119385},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41882646083831787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4178091287612915},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37337857484817505},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1047106385231018},{"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},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-023-01255-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-023-01255-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01255-5.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:358818ef39d441778ceb15dc5f6c8d1a","is_oa":true,"landing_page_url":"https://doaj.org/article/358818ef39d441778ceb15dc5f6c8d1a","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 10, Iss 2, Pp 1985-1995 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-023-01255-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-023-01255-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01255-5.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3860502462","display_name":null,"funder_award_id":"62102444","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G610216879","display_name":null,"funder_award_id":"61902425","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387740163.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W41159429","https://openalex.org/W2157488300","https://openalex.org/W2786166887","https://openalex.org/W2907627983","https://openalex.org/W2911398251","https://openalex.org/W2920054549","https://openalex.org/W2997502221","https://openalex.org/W3006430665","https://openalex.org/W3024044737","https://openalex.org/W3120265095","https://openalex.org/W3190405541","https://openalex.org/W6600135713","https://openalex.org/W6600341180","https://openalex.org/W6600474606","https://openalex.org/W6810179550","https://openalex.org/W6826287919"],"related_works":["https://openalex.org/W590788508","https://openalex.org/W4313233093","https://openalex.org/W2358082531","https://openalex.org/W2589976903","https://openalex.org/W2335596023","https://openalex.org/W2374273535","https://openalex.org/W2026719400","https://openalex.org/W2500176061","https://openalex.org/W1952244190","https://openalex.org/W2357534180"],"abstract_inverted_index":{"Abstract":[0],"Great":[1],"progress":[2],"has":[3],"been":[4],"made":[5],"in":[6,13,43,190],"the":[7,26,45,58,78,101,106,142,159,167,178,182],"domain":[8],"of":[9,29,38,41,81,184],"multi-agent":[10],"reinforcement":[11],"learning":[12,25,77,112,147],"recent":[14,212],"years.":[15],"Most":[16],"work":[17],"concentrates":[18],"on":[19,57],"solving":[20],"a":[21,39,49,73,109,122,173],"single":[22],"task":[23],"by":[24,172],"cooperative":[27,88],"behaviors":[28,53],"agents.":[30],"However,":[31],"many":[32],"real-world":[33],"problems":[34],"are":[35,62,170],"normally":[36],"composed":[37],"set":[40],"subtasks":[42],"which":[44,99],"execution":[46],"order":[47],"follows":[48],"certain":[50],"procedure.":[51],"Cooperative":[52],"should":[54],"be":[55,130],"learned":[56],"premise":[59],"that":[60,203],"agents":[61,82,95],"first":[63],"allocated":[64],"to":[65,94,116,121,132,151],"those":[66],"subtasks.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,187],"propose":[72],"hierarchical":[74,103],"framework":[75,205],"for":[76,155],"dynamic":[79],"allocation":[80,111,160],"among":[83],"subtasks,":[84],"as":[85,87],"well":[86],"behaviors.":[89],"We":[90],"design":[91],"networks":[92,164,169],"corresponding":[93],"and":[96,198],"subnetworks,":[97],"respectively,":[98],"constitute":[100],"whole":[102],"network.":[104,124],"For":[105,141],"upper":[107],"layer,":[108,144],"novel":[110],"mechanism":[113],"is":[114,149],"devised":[115],"map":[117],"an":[118,145],"agent":[119,126,157,163],"network":[120,127,136],"subtask":[123,135,168],"Each":[125],"could":[128],"only":[129,133],"assigned":[131],"one":[134],"at":[137],"each":[138,156],"time":[139],"step.":[140],"lower":[143],"action":[146],"module":[148],"designed":[150],"compute":[152],"appropriate":[153],"actions":[154],"with":[158,166],"result.":[161],"The":[162],"together":[165],"updated":[171],"common":[174],"reward":[175],"obtained":[176],"from":[177],"environment.":[179],"To":[180],"evaluate":[181],"effectiveness":[183],"our":[185,204],"framework,":[186],"conduct":[188],"experiments":[189],"two":[191],"challenging":[192],"environments,":[193],"i.e.,":[194],"Google":[195],"Research":[196],"Football":[197],"SAVETHECITY.":[199],"Empirical":[200],"results":[201],"show":[202],"achieves":[206],"much":[207],"better":[208],"performance":[209],"than":[210],"other":[211],"methods.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}