{"id":"https://openalex.org/W3166669706","doi":"https://doi.org/10.1109/access.2021.3085328","title":"Low-Cost Multi-Agent Navigation via Reinforcement Learning With Multi-Fidelity Simulator","display_name":"Low-Cost Multi-Agent Navigation via Reinforcement Learning With Multi-Fidelity Simulator","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3166669706","doi":"https://doi.org/10.1109/access.2021.3085328","mag":"3166669706"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3085328","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3085328","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09445074.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09445074.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090846991","display_name":"Jiantao Qiu","orcid":"https://orcid.org/0000-0002-1328-2639"},"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":true,"raw_author_name":"Jiantao Qiu","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054149338","display_name":"Chao Yu","orcid":"https://orcid.org/0000-0002-4279-2152"},"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":"Chao Yu","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091341521","display_name":"Weiling Liu","orcid":null},"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":"Weiling Liu","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101523128","display_name":"Tianxiang Yang","orcid":"https://orcid.org/0000-0003-3619-7725"},"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":"Tianxiang Yang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112107807","display_name":"Jincheng Yu","orcid":"https://orcid.org/0009-0007-3831-3845"},"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":"Jincheng Yu","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, 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":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023755254","display_name":"Huazhong Yang","orcid":"https://orcid.org/0000-0003-2421-353X"},"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":"Huazhong Yang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5090846991"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0928,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.390189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"9","issue":null,"first_page":"84773","last_page":"84782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9990000128746033,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8948431015014648},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.8030617237091064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7804949283599854},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6718443036079407},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.6641151905059814},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.540219247341156},{"id":"https://openalex.org/keywords/driving-simulator","display_name":"Driving simulator","score":0.41765648126602173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33669304847717285},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.12234419584274292},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11154723167419434}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8948431015014648},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.8030617237091064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804949283599854},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6718443036079407},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.6641151905059814},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.540219247341156},{"id":"https://openalex.org/C2780689630","wikidata":"https://www.wikidata.org/wiki/Q2081815","display_name":"Driving simulator","level":2,"score":0.41765648126602173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33669304847717285},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.12234419584274292},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11154723167419434},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3085328","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3085328","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09445074.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:00262cce78a64649a8011d404b48d90b","is_oa":true,"landing_page_url":"https://doaj.org/article/00262cce78a64649a8011d404b48d90b","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 84773-84782 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3085328","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3085328","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09445074.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1169439367","display_name":null,"funder_award_id":"U19B2019, 61832007","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/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3166669706.pdf","grobid_xml":"https://content.openalex.org/works/W3166669706.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1965760189","https://openalex.org/W2082511574","https://openalex.org/W2142943472","https://openalex.org/W2167340365","https://openalex.org/W2204090322","https://openalex.org/W2280163991","https://openalex.org/W2418627435","https://openalex.org/W2426267443","https://openalex.org/W2586067474","https://openalex.org/W2601465345","https://openalex.org/W2810754397","https://openalex.org/W2877093712","https://openalex.org/W2883057932","https://openalex.org/W2949267040","https://openalex.org/W2949886883","https://openalex.org/W2962769637","https://openalex.org/W2962872206","https://openalex.org/W2962887844","https://openalex.org/W2963368198","https://openalex.org/W2963428623","https://openalex.org/W2963809389","https://openalex.org/W2963821308","https://openalex.org/W2963938771","https://openalex.org/W4319988532","https://openalex.org/W6695011786","https://openalex.org/W6733118196","https://openalex.org/W6734215269","https://openalex.org/W6735698609","https://openalex.org/W6753207554","https://openalex.org/W6753264383","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W575009904","https://openalex.org/W750767097","https://openalex.org/W4313443006","https://openalex.org/W4306765721","https://openalex.org/W2945374968","https://openalex.org/W4293777179","https://openalex.org/W4385452045","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"reinforcement":[3,93],"learning":[4,94],"(RL)":[5],"has":[6],"been":[7],"widely":[8],"used":[9],"to":[10,24,54,77,89,106],"solve":[11],"multi-agent":[12,144],"navigation":[13,145],"tasks,":[14],"and":[15,30,40,111,120,136],"a":[16,50,69,99,139],"high-fidelity":[17,34],"level":[18],"for":[19],"the":[20,26,42,61,74,83,91,108,115],"simulator":[21,85,101],"is":[22],"critical":[23],"narrow":[25],"gap":[27],"between":[28],"simulation":[29],"real-world":[31],"tasks.":[32,146],"However,":[33],"simulators":[35],"have":[36],"high":[37],"sampling":[38],"costs":[39],"bottleneck":[41],"training":[43],"model-free":[44],"RL":[45],"algorithms.":[46],"Hence,":[47],"we":[48],"propose":[49],"Multi-Fidelity":[51],"Simulator":[52],"framework":[53],"train":[55],"Multi-Agent":[56],"Reinforcement":[57],"Learning":[58],"(MFS-MARL),":[59],"reducing":[60],"total":[62],"data":[63],"cost":[64,141],"with":[65,102,114],"samples":[66],"generated":[67],"by":[68],"low-fidelity":[70,84],"simulator.":[71],"We":[72,97],"apply":[73],"depth-first":[75],"search":[76],"obtain":[78,132],"local":[79,133],"feasible":[80,134],"policies":[81,88,135],"on":[82],"as":[86],"expert":[87,121],"help":[90],"original":[92],"algorithm":[95],"explore.":[96],"built":[98],"multi-vehicle":[100],"variable":[103],"fidelity":[104],"levels":[105],"test":[107],"proposed":[109],"method":[110,129],"compared":[112],"it":[113],"vanilla":[116],"Soft":[117],"Actor-Critic":[118],"(SAC)":[119],"actor":[122],"methods.":[123],"The":[124],"results":[125],"show":[126],"that":[127],"our":[128],"can":[130,137],"effectively":[131],"achieve":[138],"23%":[140],"reduction":[142],"in":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}