{"id":"https://openalex.org/W3093345403","doi":"https://doi.org/10.1109/lra.2021.3068952","title":"Decentralized Multi-Agent Pursuit Using Deep Reinforcement Learning","display_name":"Decentralized Multi-Agent Pursuit Using Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-03-25","ids":{"openalex":"https://openalex.org/W3093345403","doi":"https://doi.org/10.1109/lra.2021.3068952","mag":"3093345403"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3068952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3068952","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.08193","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Cristino de Souza","orcid":null},"institutions":[{"id":"https://openalex.org/I102516824","display_name":"Universit\u00e9 de Technologie de Compi\u00e8gne","ror":"https://ror.org/04y5kwa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I102516824"]},{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["AE","FR"],"is_corresponding":true,"raw_author_name":"Cristino de Souza","raw_affiliation_strings":["Technology Innovation Institute, Abu Dhabi, UAE","Universit\u00e9 de Technologie de Compi\u00e8gne, CNRS, Heudiasyc, CS, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210087059"]},{"raw_affiliation_string":"Universit\u00e9 de Technologie de Compi\u00e8gne, CNRS, Heudiasyc, CS, France","institution_ids":["https://openalex.org/I102516824","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rhys Newbury","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rhys Newbury","raw_affiliation_strings":["Department of Electrical and Computer System Engineering, Monash University, Clayton, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer System Engineering, Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Akansel Cosgun","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Akansel Cosgun","raw_affiliation_strings":["Department of Electrical and Computer System Engineering, Monash University, Clayton, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer System Engineering, Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pedro Castillo","orcid":null},"institutions":[{"id":"https://openalex.org/I102516824","display_name":"Universit\u00e9 de Technologie de Compi\u00e8gne","ror":"https://ror.org/04y5kwa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I102516824"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pedro Castillo","raw_affiliation_strings":["Universit\u00e9 de Technologie de Compi\u00e8gne, CNRS, Heudiasyc, CS, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Technologie de Compi\u00e8gne, CNRS, Heudiasyc, CS, France","institution_ids":["https://openalex.org/I102516824","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Boris Vidolov","orcid":null},"institutions":[{"id":"https://openalex.org/I102516824","display_name":"Universit\u00e9 de Technologie de Compi\u00e8gne","ror":"https://ror.org/04y5kwa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I102516824"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Boris Vidolov","raw_affiliation_strings":["Universit\u00e9 de Technologie de Compi\u00e8gne, CNRS, Heudiasyc, CS, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Technologie de Compi\u00e8gne, CNRS, Heudiasyc, CS, France","institution_ids":["https://openalex.org/I102516824","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":null,"display_name":"Dana Kuli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dana Kuli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102516824","https://openalex.org/I1294671590","https://openalex.org/I4210087059"],"apc_list":null,"apc_paid":null,"fwci":102.9109,"has_fulltext":false,"cited_by_count":158,"citation_normalized_percentile":{"value":0.99945099,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"6","issue":"3","first_page":"4552","last_page":"4559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.8826000094413757,"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"}},"topics":[{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.8826000094413757,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.04410000145435333,"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":0.008299999870359898,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.828000009059906},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.535099983215332},{"id":"https://openalex.org/keywords/pursuer","display_name":"Pursuer","score":0.4984000027179718},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.44769999384880066},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4438000023365021},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.375},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3560999929904938},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.31380000710487366}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.828000009059906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639000177383423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6474000215530396},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C2776927521","wikidata":"https://www.wikidata.org/wiki/Q468489","display_name":"Pursuer","level":2,"score":0.4984000027179718},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4438000023365021},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.375},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.336899995803833},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/lra.2021.3068952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3068952","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2010.08193","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.08193","pdf_url":"https://arxiv.org/pdf/2010.08193","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-03561689v1","is_oa":false,"landing_page_url":"https://hal-cnrs.archives-ouvertes.fr/hal-03561689","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 2377-3766","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:HAL:hal-03584945v1","is_oa":false,"landing_page_url":"https://cnrs.hal.science/hal-03584945","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Robotics and Automation (ICRA 2021), May 2021, Xi'an, China. pp.4552-4559, ⟨10.1109/LRA.2021.3068952⟩","raw_type":"Conference papers"},{"id":"pmh:oai:HAL:hal-03842721v1","is_oa":true,"landing_page_url":"https://cnrs.hal.science/hal-03842721","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Robotics and Automation Letters, 2021, 6 (3), pp.4552-4559. ⟨10.1109/LRA.2021.3068952⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.08193","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.08193","pdf_url":"https://arxiv.org/pdf/2010.08193","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W40650588","https://openalex.org/W1672238326","https://openalex.org/W1677859417","https://openalex.org/W2015410655","https://openalex.org/W2016437006","https://openalex.org/W2020778932","https://openalex.org/W2023775503","https://openalex.org/W2050044094","https://openalex.org/W2105850748","https://openalex.org/W2131774270","https://openalex.org/W2296073425","https://openalex.org/W2305205647","https://openalex.org/W2331855880","https://openalex.org/W2498529546","https://openalex.org/W2502930595","https://openalex.org/W2528107617","https://openalex.org/W2567355071","https://openalex.org/W2567811016","https://openalex.org/W2772042733","https://openalex.org/W2883532348","https://openalex.org/W2889656043","https://openalex.org/W2909445258","https://openalex.org/W2963099939","https://openalex.org/W2972273284","https://openalex.org/W2990123902","https://openalex.org/W3005152498","https://openalex.org/W3040707741","https://openalex.org/W4230799304","https://openalex.org/W6644827127","https://openalex.org/W6684921986","https://openalex.org/W6736021936","https://openalex.org/W6738796088","https://openalex.org/W6744580074","https://openalex.org/W6746015766","https://openalex.org/W6748839928","https://openalex.org/W6752818329","https://openalex.org/W6757374366","https://openalex.org/W6763101028","https://openalex.org/W6767919266","https://openalex.org/W6783876633"],"related_works":[],"abstract_inverted_index":{"Pursuit-evasion":[0],"is":[1,115],"the":[2,119],"problem":[3],"of":[4,46,109],"capturing":[5],"mobile":[6],"targets":[7],"with":[8,23,85,125],"one":[9],"or":[10],"more":[11],"pursuers.":[12],"We":[13,34],"use":[14,35],"deep":[15],"reinforcement":[16,101],"learning":[17,102],"for":[18,42],"pursuing":[19],"an":[20],"omnidirectional":[21],"target":[22],"multiple,":[24],"homogeneous":[25],"agents":[26],"that":[27,72,95],"are":[28],"subject":[29],"to":[30,38,63,91,118],"unicycle":[31],"kinematic":[32],"constraints.":[33],"shared":[36],"experience":[37],"train":[39],"a":[40,43,60,69,74,86,122],"policy":[41,114],"given":[44],"number":[45],"pursuers,":[47],"executed":[48],"independently":[49],"by":[50],"each":[51],"agent":[52],"at":[53],"run-time.":[54],"The":[55,112],"training":[56],"uses":[57],"curriculum":[58],"learning,":[59],"sweeping-angle":[61],"ordering":[62],"locally":[64],"represent":[65],"neighboring":[66],"agents,":[67],"and":[68,77,80,89],"reward":[70],"structure":[71],"encourages":[73],"good":[75],"formation":[76],"combines":[78],"individual":[79],"group":[81],"rewards.":[82],"Simulated":[83],"experiments":[84],"reactive":[87],"evader":[88],"up":[90],"eight":[92],"pursuers":[93],"show":[94],"our":[96],"learning-based":[97],"approach":[98],"outperforms":[99],"recent":[100],"techniques":[103],"as":[104,106],"well":[105],"non-holonomic":[107],"adaptations":[108],"classical":[110],"algorithms.":[111],"learned":[113],"successfully":[116],"transferred":[117],"real-world":[120],"in":[121],"proof-of-concept":[123],"demonstration":[124],"three":[126],"motion-constrained":[127],"pursuer":[128],"drones.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":54},{"year":2024,"cited_by_count":38},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":5}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2020-10-22T00:00:00"}