{"id":"https://openalex.org/W4407247154","doi":"https://doi.org/10.1109/tcds.2025.3540071","title":"Decentralized Reinforcement Learning for Multiple Robotic Fish in Cooperative Pursuit Task","display_name":"Decentralized Reinforcement Learning for Multiple Robotic Fish in Cooperative Pursuit Task","publication_year":2025,"publication_date":"2025-02-07","ids":{"openalex":"https://openalex.org/W4407247154","doi":"https://doi.org/10.1109/tcds.2025.3540071"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2025.3540071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3540071","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Transactions on Cognitive and Developmental Systems","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/A5014555721","display_name":"Yukai Feng","orcid":"https://orcid.org/0009-0005-3766-3793"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yukai Feng","raw_affiliation_strings":["Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-3766-3793","affiliations":[{"raw_affiliation_string":"Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001123312","display_name":"Zhengxing Wu","orcid":"https://orcid.org/0000-0003-2338-5217"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengxing Wu","raw_affiliation_strings":["Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2338-5217","affiliations":[{"raw_affiliation_string":"Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jian Wang","orcid":"https://orcid.org/0000-0003-3742-9671"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3742-9671","affiliations":[{"raw_affiliation_string":"Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111119282","display_name":"Sijie Li","orcid":"https://orcid.org/0009-0001-9523-5210"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sijie Li","raw_affiliation_strings":["Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-9523-5210","affiliations":[{"raw_affiliation_string":"Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044143142","display_name":"Yupei Huang","orcid":"https://orcid.org/0000-0002-3173-3245"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupei Huang","raw_affiliation_strings":["Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3173-3245","affiliations":[{"raw_affiliation_string":"Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073958329","display_name":"Junzhi Yu","orcid":"https://orcid.org/0000-0002-6347-572X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4391767778","display_name":"State Key Laboratory of Turbulence and Complex Systems","ror":"https://ror.org/04km98768","country_code":null,"type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhi Yu","raw_affiliation_strings":["State Key Laboratory for Turbulence and Complex Systems, Department of Advanced Manufacturing and Robotics, College of Engineering, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6347-572X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Turbulence and Complex Systems, Department of Advanced Manufacturing and Robotics, College of Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024708104","display_name":"Min Tan","orcid":"https://orcid.org/0000-0002-1986-8438"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Tan","raw_affiliation_strings":["Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1986-8438","affiliations":[{"raw_affiliation_string":"Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5014555721"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":1.3517,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78586706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"17","issue":"4","first_page":"1022","last_page":"1034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9857000112533569,"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":0.9857000112533569,"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":0.9850999712944031,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/computer-science","display_name":"Computer science","score":0.8285989761352539},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7837866544723511},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6085845232009888},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40545955300331116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3411881923675537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8285989761352539},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7837866544723511},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6085845232009888},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40545955300331116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3411881923675537},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2025.3540071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3540071","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5012687669","display_name":null,"funder_award_id":"62203436","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7596075617","display_name":null,"funder_award_id":"62233001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7842586755","display_name":null,"funder_award_id":"2023039","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G8748815676","display_name":null,"funder_award_id":"62033013","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/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1512273979","https://openalex.org/W1990753492","https://openalex.org/W2000076730","https://openalex.org/W2023775503","https://openalex.org/W2046127725","https://openalex.org/W2092289967","https://openalex.org/W2137633045","https://openalex.org/W2148479241","https://openalex.org/W2223927396","https://openalex.org/W2808873073","https://openalex.org/W2809216847","https://openalex.org/W2855449108","https://openalex.org/W2914309011","https://openalex.org/W2963821308","https://openalex.org/W3035829937","https://openalex.org/W3037033265","https://openalex.org/W3045180775","https://openalex.org/W3046106022","https://openalex.org/W3046385005","https://openalex.org/W3082038112","https://openalex.org/W3090424311","https://openalex.org/W3093345403","https://openalex.org/W3107524692","https://openalex.org/W3119182912","https://openalex.org/W3125355781","https://openalex.org/W3195439150","https://openalex.org/W3205608407","https://openalex.org/W3208081444","https://openalex.org/W4205812179","https://openalex.org/W4221155562","https://openalex.org/W4285138842","https://openalex.org/W4321763414","https://openalex.org/W4362538178","https://openalex.org/W4366983190","https://openalex.org/W4377000489","https://openalex.org/W4383108558","https://openalex.org/W4385275321","https://openalex.org/W4389776873","https://openalex.org/W4392004031","https://openalex.org/W6738796088"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"The":[0],"control":[1],"of":[2,27,72,115,127],"multirobot":[3],"systems,":[4],"particularly":[5],"in":[6,17,136,148],"the":[7,24,36,66,125,128],"pursuit-evasion":[8],"(PE)":[9],"with":[10,81],"multiple":[11,82,150],"robots,":[12],"has":[13],"gained":[14],"significant":[15],"attention":[16],"both":[18],"academic":[19],"and":[20,40,69,106,118,131],"nonacademic":[21],"settings.":[22],"However,":[23],"collaborative":[25],"operation":[26],"multirobotic":[28],"fish":[29],"systems":[30],"encounters":[31],"substantial":[32],"challenges":[33],"due":[34],"to":[35,55,123],"complex":[37],"underwater":[38,61,137,149],"environment":[39,80],"unique":[41],"movement":[42],"mode.":[43],"In":[44],"this":[45],"article,":[46],"we":[47,75,94],"propose":[48],"a":[49,57,77,87,96,113],"multiagent":[50],"reinforcement":[51],"learning":[52,99],"(MARL)":[53],"approach":[54],"develop":[56,95],"viable":[58],"strategy":[59,98],"for":[60,109,145],"cooperative":[62],"pursuit.":[63],"Initially,":[64],"considering":[65],"hydrodynamic":[67],"model":[68],"motion":[70],"characteristics":[71],"robotic":[73],"fish,":[74],"construct":[76],"specific":[78],"simulation":[79],"fish-like":[83],"agents,":[84],"which":[85],"provides":[86],"highly":[88],"realistic":[89],"state":[90],"transition":[91],"model.":[92],"Next,":[93],"MARL-based":[97],"framework":[100],"that":[101],"incorporates":[102],"appropriate":[103],"reward":[104],"functions":[105],"agent":[107],"actions":[108],"policy":[110],"learning.":[111],"Finally,":[112],"series":[114],"comprehensive":[116],"simulations":[117],"practical":[119],"experiments":[120],"are":[121],"conducted":[122],"validate":[124],"effectiveness":[126],"proposed":[129],"method":[130],"confirm":[132],"its":[133],"successful":[134],"application":[135],"pursuit":[138],"scenarios.":[139],"These":[140],"findings":[141],"offer":[142],"valuable":[143],"insights":[144],"further":[146],"research":[147],"robot":[151],"systems.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}