{"id":"https://openalex.org/W4320015948","doi":"https://doi.org/10.1109/jiot.2023.3240671","title":"Improving Sample Efficiency of Multiagent Reinforcement Learning With Nonexpert Policy for Flocking Control","display_name":"Improving Sample Efficiency of Multiagent Reinforcement Learning With Nonexpert Policy for Flocking Control","publication_year":2023,"publication_date":"2023-01-30","ids":{"openalex":"https://openalex.org/W4320015948","doi":"https://doi.org/10.1109/jiot.2023.3240671"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2023.3240671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2023.3240671","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-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/A5089892883","display_name":"Yunbo Qiu","orcid":"https://orcid.org/0000-0001-5069-6673"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Qiu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5069-6673","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067942871","display_name":"Yue Jin","orcid":"https://orcid.org/0000-0002-0344-4868"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Jin","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050690756","display_name":"Lebin Yu","orcid":"https://orcid.org/0000-0003-4566-3820"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lebin Yu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4566-3820","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370361","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0001-7683-6937"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7683-6937","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6108-5157","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441855","display_name":"Xudong Zhang","orcid":"https://orcid.org/0000-0002-6465-7437"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6465-7437","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.9656,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.94483116,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"10","issue":"16","first_page":"14014","last_page":"14027"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/flocking","display_name":"Flocking (texture)","score":0.9298378825187683},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7782071828842163},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6755773425102234},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5387251377105713},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.48117193579673767},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42379987239837646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3907434940338135},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3236575126647949},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13261061906814575}],"concepts":[{"id":"https://openalex.org/C2781220375","wikidata":"https://www.wikidata.org/wiki/Q814208","display_name":"Flocking (texture)","level":2,"score":0.9298378825187683},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7782071828842163},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6755773425102234},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5387251377105713},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.48117193579673767},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42379987239837646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3907434940338135},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3236575126647949},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13261061906814575},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2023.3240671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2023.3240671","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2511730577","display_name":null,"funder_award_id":"M-0248","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6839492696","display_name":null,"funder_award_id":"U19B2019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8262591375","display_name":null,"funder_award_id":"62104128","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8338455073","display_name":null,"funder_award_id":"62203257","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"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320327539","display_name":"Beijing Innovation Center for Future Chip","ror":null},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1548913039","https://openalex.org/W1754560090","https://openalex.org/W1896299845","https://openalex.org/W1921138517","https://openalex.org/W1990193153","https://openalex.org/W1998030085","https://openalex.org/W2098774185","https://openalex.org/W2124394479","https://openalex.org/W2130647945","https://openalex.org/W2150312211","https://openalex.org/W2153809277","https://openalex.org/W2167224731","https://openalex.org/W2170427350","https://openalex.org/W2773333411","https://openalex.org/W2806824292","https://openalex.org/W2883057932","https://openalex.org/W2918849077","https://openalex.org/W2922306179","https://openalex.org/W2949886883","https://openalex.org/W2954085204","https://openalex.org/W2963099939","https://openalex.org/W2963277051","https://openalex.org/W2978148161","https://openalex.org/W2981655159","https://openalex.org/W2982316857","https://openalex.org/W2989367523","https://openalex.org/W3005654113","https://openalex.org/W3010961334","https://openalex.org/W3012398038","https://openalex.org/W3035458768","https://openalex.org/W3037625705","https://openalex.org/W3044457827","https://openalex.org/W3048703323","https://openalex.org/W3056510116","https://openalex.org/W3113915485","https://openalex.org/W3131197284","https://openalex.org/W3172360140","https://openalex.org/W3174645049","https://openalex.org/W3183210514","https://openalex.org/W3185856055","https://openalex.org/W4214717370","https://openalex.org/W4287588601","https://openalex.org/W4299802797","https://openalex.org/W4309344700","https://openalex.org/W4312823498","https://openalex.org/W4317350110","https://openalex.org/W6632828981","https://openalex.org/W6637569971","https://openalex.org/W6674884181","https://openalex.org/W6682677477","https://openalex.org/W6684338915","https://openalex.org/W6718092244","https://openalex.org/W6735698609","https://openalex.org/W6738796088","https://openalex.org/W6753207554","https://openalex.org/W6768731700","https://openalex.org/W6768977950","https://openalex.org/W6787554102","https://openalex.org/W6796589144","https://openalex.org/W6981852861"],"related_works":["https://openalex.org/W3196562632","https://openalex.org/W1989157904","https://openalex.org/W2530977643","https://openalex.org/W4318822799","https://openalex.org/W1481047111","https://openalex.org/W3048440450","https://openalex.org/W2357545018","https://openalex.org/W3099149755","https://openalex.org/W2021478294","https://openalex.org/W2139131532"],"abstract_inverted_index":{"Control":[0],"algorithms":[1],"of":[2,13,39,75,94,105,181,203,209,211],"a":[3,28,52,91,123,128,216],"multiagent":[4,67],"system":[5],"(MAS)":[6],"have":[7],"been":[8],"applied":[9],"to":[10,33,45,51,82,117,147,160,177],"many":[11],"Internet":[12],"Things":[14],"devices,":[15],"such":[16],"as":[17],"unmanned":[18],"aerial":[19],"vehicles":[20],"and":[21,37,55,80,98,127,192,206,215],"autonomous":[22],"underwater":[23],"vehicles.":[24],"Flocking":[25],"control":[26,77],"is":[27,169],"crucial":[29],"problem":[30,74,104,180],"in":[31,102,171,195],"MAS":[32],"enhance":[34],"the":[35,43,47,61,73,87,99,103,144,162,166,179,201,207,212],"safety":[36],"cooperativity":[38],"agents,":[40,149],"which":[41,121],"requires":[42],"agents":[44,97,159,205],"maintain":[46],"flock":[48],"when":[49],"navigating":[50],"target":[53],"position":[54],"avoiding":[56],"collisions.":[57],"In":[58,108],"comparison":[59],"with":[60],"traditional":[62],"algorithms,":[63],"methods":[64,89],"based":[65],"on":[66],"reinforcement":[68],"learning":[69],"(MARL)":[70],"can":[71,133],"solve":[72,178],"flocking":[76,182,196],"more":[78,83,204],"flexibly":[79],"adapt":[81],"complex":[84],"environments.":[85],"However,":[86],"MARL-based":[88],"demand":[90],"huge":[92],"number":[93],"interactions":[95],"between":[96],"environment,":[100],"resulting":[101],"sample":[106,119,190],"inefficiency.":[107],"this":[109],"article,":[110],"we":[111],"propose":[112],"nonexpert":[113,145,163,167,213],"policy-aided":[114],"MARL":[115,125,138,218],"(NPA-MARL)":[116],"improve":[118],"efficiency,":[120],"utilizes":[122],"fundamental":[124,217],"algorithm":[126],"prior":[129],"policy":[130,146,164,168,193,214],"whose":[131],"performance":[132,194],"be":[134],"nonexpert.":[135],"Before":[136],"online":[137,155],"training,":[139,156],"NPA-MARL":[140,157,176,188,199],"generates":[141],"demonstrations":[142],"by":[143],"pretrain":[148],"while":[150],"preventing":[151],"overfitting":[152],"demonstrations.":[153],"During":[154],"instructs":[158],"imitate":[161],"if":[165],"better":[170],"agents\u2019":[172],"recognition.":[173],"We":[174],"leverage":[175],"control.":[183,197],"Experimental":[184],"results":[185],"show":[186],"that":[187],"improves":[189],"efficiency":[191],"Besides,":[198],"has":[200],"scalability":[202],"flexibility":[208],"choice":[210],"algorithm.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}