{"id":"https://openalex.org/W4309344700","doi":"https://doi.org/10.1109/smc53654.2022.9945272","title":"Sub-optimal Policy Aided Multi-Agent Reinforcement Learning for Flocking Control","display_name":"Sub-optimal Policy Aided Multi-Agent Reinforcement Learning for Flocking Control","publication_year":2022,"publication_date":"2022-10-09","ids":{"openalex":"https://openalex.org/W4309344700","doi":"https://doi.org/10.1109/smc53654.2022.9945272"},"language":"en","primary_location":{"id":"doi:10.1109/smc53654.2022.9945272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53654.2022.9945272","pdf_url":null,"source":{"id":"https://openalex.org/S4363607746","display_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"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":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"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/A5100370410","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-1543-2434"},"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":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"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/A5107862315","display_name":"Xudong Zhang","orcid":"https://orcid.org/0009-0002-8631-3632"},"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":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"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":0.8088,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66991331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2709","last_page":"2714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962999820709229,"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/T11133","display_name":"UAV Applications and Optimization","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/flocking","display_name":"Flocking (texture)","score":0.9048464298248291},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8940823078155518},{"id":"https://openalex.org/keywords/marl","display_name":"Marl","score":0.6301040649414062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6155255436897278},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6008024215698242},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5170972347259521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.418276846408844},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3752829134464264},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3359224498271942},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16886404156684875}],"concepts":[{"id":"https://openalex.org/C2781220375","wikidata":"https://www.wikidata.org/wiki/Q814208","display_name":"Flocking (texture)","level":2,"score":0.9048464298248291},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8940823078155518},{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.6301040649414062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6155255436897278},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6008024215698242},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5170972347259521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.418276846408844},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3752829134464264},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3359224498271942},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16886404156684875},{"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/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53654.2022.9945272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53654.2022.9945272","pdf_url":null,"source":{"id":"https://openalex.org/S4363607746","display_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1548913039","https://openalex.org/W1921138517","https://openalex.org/W2150312211","https://openalex.org/W2167224731","https://openalex.org/W2170427350","https://openalex.org/W2883057932","https://openalex.org/W2918849077","https://openalex.org/W2949886883","https://openalex.org/W2963099939","https://openalex.org/W2981655159","https://openalex.org/W2989367523","https://openalex.org/W3005654113","https://openalex.org/W3035458768","https://openalex.org/W3037625705","https://openalex.org/W3044457827","https://openalex.org/W3048703323","https://openalex.org/W3056510116","https://openalex.org/W3172360140","https://openalex.org/W3174645049","https://openalex.org/W4299802797","https://openalex.org/W6632828981","https://openalex.org/W6684338915","https://openalex.org/W6735698609","https://openalex.org/W6738796088","https://openalex.org/W6753207554","https://openalex.org/W6768977950","https://openalex.org/W6796589144"],"related_works":["https://openalex.org/W2126019709","https://openalex.org/W1702901972","https://openalex.org/W4249798507","https://openalex.org/W2069775250","https://openalex.org/W2152754392","https://openalex.org/W2196316523","https://openalex.org/W1989172970","https://openalex.org/W1899363654","https://openalex.org/W2507089433","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Flocking":[0],"control":[1,142,146],"is":[2,133,153],"a":[3,17,54,67,83,94,157],"challenging":[4],"problem,":[5],"where":[6,102],"multiple":[7],"agents,":[8],"such":[9],"as":[10],"drones":[11],"or":[12,91],"vehicles,":[13],"need":[14],"to":[15,76,97,138,155],"reach":[16],"target":[18],"position":[19],"while":[20],"maintaining":[21],"the":[22,34,62,103,106,113,118,126,130,140,167,173,177],"flock":[23],"and":[24,29,61,121,123,170,176],"avoiding":[25],"collisions":[26,30],"with":[27,93],"obstacles":[28],"among":[31],"agents":[32,60,99],"in":[33,43,100,115],"environment.":[35,63],"Multi-agent":[36],"reinforcement":[37,51,72],"learning":[38,52,73],"has":[39],"achieved":[40],"promising":[41],"performance":[42,104,116],"flocking":[44,141],"control.":[45],"However,":[46],"methods":[47],"based":[48,148],"on":[49,149],"traditional":[50,145],"require":[53],"considerable":[55],"number":[56],"of":[57,105],"interactions":[58],"between":[59,117],"This":[64],"paper":[65],"proposes":[66],"sub-optimal":[68,119,127,158,179],"policy":[69,85,107,120,128,132],"aided":[70],"multiagent":[71],"algorithm":[74],"(SPA-MARL)":[75],"boost":[77],"sample":[78],"efficiency.":[79],"SPA-MARL":[80,111,137,163],"directly":[81],"leverages":[82],"prior":[84],"that":[86,162],"can":[87,108,164],"be":[88,109],"manually":[89],"designed":[90],"solved":[92],"non-learning":[95],"method":[96,147],"aid":[98],"learning,":[101],"sub-optimal.":[110],"recognizes":[112],"difference":[114],"itself,":[122],"then":[124],"imitates":[125],"if":[129],"suboptimal":[131],"better.":[134],"We":[135],"leverage":[136],"solve":[139],"problem.":[143],"A":[144],"artificial":[150],"potential":[151],"fields":[152],"used":[154,178],"generate":[156],"policy.":[159,180],"Experiments":[160],"demonstrate":[161],"speed":[165],"up":[166],"training":[168],"process":[169],"outperform":[171],"both":[172],"MARL":[174],"baseline":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}