{"id":"https://openalex.org/W4200120727","doi":"https://doi.org/10.1007/s40747-021-00591-8","title":"Continuous self-adaptive optimization to learn multi-task multi-agent","display_name":"Continuous self-adaptive optimization to learn multi-task multi-agent","publication_year":2021,"publication_date":"2021-12-17","ids":{"openalex":"https://openalex.org/W4200120727","doi":"https://doi.org/10.1007/s40747-021-00591-8"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-021-00591-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-021-00591-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-021-00591-8.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 &amp; 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/s40747-021-00591-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003633201","display_name":"Wenqian Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenqian Liang","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, 410000, China","North Automatic Control Technology Institute, Taiyuan, 030000, China"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"North Automatic Control Technology Institute, Taiyuan, 030000, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046184004","display_name":"Ji Wang","orcid":"https://orcid.org/0000-0002-4199-2793"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Wang","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, 410000, China"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002192584","display_name":"Weidong Bao","orcid":"https://orcid.org/0000-0003-1867-3660"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Bao","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, 410000, China"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063946308","display_name":"Xiaomin Zhu","orcid":"https://orcid.org/0000-0003-1301-7840"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomin Zhu","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, 410000, China"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101530677","display_name":"Qingyong Wang","orcid":"https://orcid.org/0000-0001-5115-6425"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyong Wang","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, 410000, China"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024445374","display_name":"Beibei Han","orcid":"https://orcid.org/0000-0001-5729-6947"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beibei Han","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, 410000, China"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, 410000, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003633201"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.6999,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77220828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"8","issue":"2","first_page":"1355","last_page":"1367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9848999977111816,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.980400025844574,"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":0.8067314624786377},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7627362608909607},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7184369564056396},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7041434645652771},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6861039400100708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5503935813903809},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5470933318138123},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5243611335754395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48146095871925354},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3384656310081482},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09226986765861511}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8067314624786377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7627362608909607},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7184369564056396},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7041434645652771},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6861039400100708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5503935813903809},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5470933318138123},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5243611335754395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48146095871925354},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3384656310081482},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09226986765861511},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s40747-021-00591-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-021-00591-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-021-00591-8.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 &amp; Intelligent Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s40747-021-00591-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-021-00591-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-021-00591-8.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 &amp; Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G29479285","display_name":null,"funder_award_id":"ZK19-03","funder_id":"https://openalex.org/F4320324150","funder_display_name":"National University of Defense Technology"},{"id":"https://openalex.org/G4708781224","display_name":null,"funder_award_id":"ZK19-03","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5266404985","display_name":null,"funder_award_id":"62002369","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5833426455","display_name":null,"funder_award_id":"71702186","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5875052161","display_name":null,"funder_award_id":"2019-JCJQ-ZD","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6688104968","display_name":null,"funder_award_id":"620023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8814911009","display_name":null,"funder_award_id":"71702186","funder_id":"https://openalex.org/F4320324150","funder_display_name":"National University of Defense Technology"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324150","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200120727.pdf","grobid_xml":"https://content.openalex.org/works/W4200120727.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W112971866","https://openalex.org/W2031727428","https://openalex.org/W2089217417","https://openalex.org/W2145339207","https://openalex.org/W2169743339","https://openalex.org/W2617547828","https://openalex.org/W2949945034","https://openalex.org/W2962807656","https://openalex.org/W2963167310","https://openalex.org/W2968021416","https://openalex.org/W2980297462","https://openalex.org/W2996786181","https://openalex.org/W2997536466","https://openalex.org/W3021988786","https://openalex.org/W3023726311","https://openalex.org/W3047052905","https://openalex.org/W3089882944","https://openalex.org/W3131491648","https://openalex.org/W6605730092","https://openalex.org/W6794089036","https://openalex.org/W6811851346"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Abstract":[0],"Multi-agent":[1],"reinforcement":[2],"learning":[3,19],"(MARL)":[4],"methods":[5],"have":[6,49],"shown":[7],"superior":[8],"performance":[9,44,136],"to":[10,31,50,75,122,125,131],"solve":[11],"a":[12,85,99,112,150,168],"variety":[13],"of":[14,62,161,170],"real-world":[15],"problems":[16,28],"focusing":[17],"on":[18,137],"distinct":[20],"policies":[21,55,89,110],"for":[22,56,157],"individual":[23,57],"tasks.":[24,128],"These":[25],"approaches":[26],"face":[27],"when":[29],"applied":[30],"the":[32,71,82,119,133,142],"non-stationary":[33],"real-world:":[34],"agents":[35,48,171],"trained":[36],"in":[37,67,78],"specialized":[38,54],"tasks":[39,63,77],"cannot":[40,106],"achieve":[41],"satisfied":[42],"generalization":[43],"across":[45,184],"multiple":[46,76],"tasks;":[47],"learn":[51],"and":[52,59,148],"store":[53],"task":[58],"reliable":[60],"identities":[61],"are":[64,90],"hardly":[65],"observable":[66],"practice.":[68],"To":[69],"address":[70],"challenge":[72],"continuously":[73,123],"adapting":[74],"MARL,":[79],"we":[80,97,140],"formalize":[81],"problem":[83],"into":[84,111],"two-stage":[86],"curriculum.":[87],"Single-task":[88],"learned":[91],"with":[92,167],"MARL":[93],"approaches,":[94],"after":[95],"that":[96,105,173],"develop":[98,149],"gradient-based":[100],"Self-Adaptive":[101],"Meta-Learning":[102],"algorithm,":[103],"SAML,":[104],"only":[107],"distill":[108],"single-task":[109],"unified":[113,120],"policy":[114,121],"but":[115],"also":[116],"can":[117],"facilitate":[118],"adapt":[124],"new":[126,151],"incoming":[127],"In":[129],"addition,":[130],"validate":[132],"continuous":[134,162],"adaptation":[135,163,180],"complex":[138],"task,":[139],"extend":[141],"widely":[143],"adopted":[144],"StarCraft":[145,154],"benchmark":[146],"SMAC":[147],"multi-task":[152],"multi-agent":[153],"environment,":[155],"Meta-SMAC,":[156],"testing":[158],"various":[159],"aspects":[160],"method.":[164],"Our":[165],"experiments":[166],"population":[169],"show":[172],"our":[174],"method":[175],"enables":[176],"significantly":[177],"more":[178],"efficient":[179],"than":[181],"reactive":[182],"baselines":[183],"different":[185],"scenarios.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
