{"id":"https://openalex.org/W4312755930","doi":"https://doi.org/10.1109/ijcnn55064.2022.9891898","title":"Multi-Virtual-Agent Reinforcement Learning for a Stochastic Predator-Prey Grid Environment","display_name":"Multi-Virtual-Agent Reinforcement Learning for a Stochastic Predator-Prey Grid Environment","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312755930","doi":"https://doi.org/10.1109/ijcnn55064.2022.9891898"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9891898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9891898","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5101083689","display_name":"Yanbin Lin","orcid":"https://orcid.org/0000-0002-3485-8967"},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yanbin Lin","raw_affiliation_strings":["Electrical Engineering and Computer Science Florida Atlantic University,Boca Raton,FL,USA,33431"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Florida Atlantic University,Boca Raton,FL,USA,33431","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075006150","display_name":"Zhen Ni","orcid":"https://orcid.org/0000-0003-3166-4726"},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhen Ni","raw_affiliation_strings":["Electrical Engineering and Computer Science Florida Atlantic University,Boca Raton,FL,USA,33431"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Florida Atlantic University,Boca Raton,FL,USA,33431","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010882980","display_name":"X. Zhong","orcid":"https://orcid.org/0000-0002-8367-0215"},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangnan Zhong","raw_affiliation_strings":["Electrical Engineering and Computer Science Florida Atlantic University,Boca Raton,FL,USA,33431"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Florida Atlantic University,Boca Raton,FL,USA,33431","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101083689"],"corresponding_institution_ids":["https://openalex.org/I63772739"],"apc_list":null,"apc_paid":null,"fwci":0.3118,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52547942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9707000255584717,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9265880584716797},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8155556321144104},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6930738091468811},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5596195459365845},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5501936674118042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5173670649528503},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3357793092727661},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07147783041000366}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9265880584716797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155556321144104},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6930738091468811},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5596195459365845},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5501936674118042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5173670649528503},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3357793092727661},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07147783041000366},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9891898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9891898","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G302519468","display_name":null,"funder_award_id":"2047064,2047010,1947419,1947418","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1641379095","https://openalex.org/W1649854525","https://openalex.org/W1988688219","https://openalex.org/W2038503397","https://openalex.org/W2113913482","https://openalex.org/W2168565265","https://openalex.org/W2214065353","https://openalex.org/W2582946978","https://openalex.org/W2594794854","https://openalex.org/W2604763608","https://openalex.org/W2767050701","https://openalex.org/W2894976951","https://openalex.org/W2964043796","https://openalex.org/W2964098908","https://openalex.org/W3003168199","https://openalex.org/W3006993751","https://openalex.org/W3036746461","https://openalex.org/W3101442004","https://openalex.org/W3116525149","https://openalex.org/W3121342653","https://openalex.org/W3182582186","https://openalex.org/W4214717370","https://openalex.org/W6677067356","https://openalex.org/W6692846177","https://openalex.org/W6735011893","https://openalex.org/W6736057607","https://openalex.org/W6747901993","https://openalex.org/W6755069753","https://openalex.org/W6798926350"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4377293004","https://openalex.org/W4206669594","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W2380963126","https://openalex.org/W2160425906","https://openalex.org/W2385207382","https://openalex.org/W1544908136","https://openalex.org/W2102737958"],"abstract_inverted_index":{"Generalization":[0],"problem":[1],"of":[2,77,111,136,162],"reinforcement":[3,12,41,112,148,163],"learning":[4,13,42,113,149,164],"is":[5],"crucial":[6],"especially":[7],"for":[8,45],"dynamic":[9,29,115],"environments.":[10],"Conventional":[11],"methods":[14],"solve":[15],"the":[16,55,60,94,98,108,120,134,137,143,146,160,169],"problems":[17],"with":[18,70,93,145],"some":[19],"ideal":[20],"assumptions":[21],"and":[22,91,166],"are":[23,127],"difficult":[24],"to":[25,68,132,168,171],"be":[26],"applied":[27],"in":[28,74,114,129],"environments":[30,73],"directly.":[31],"In":[32],"this":[33,130],"paper,":[34],"we":[35,64],"propose":[36],"a":[37,46,82],"new":[38],"multi-virtual-":[39],"agent":[40,84],"(MVARL)":[43],"approach":[44],"predator-prey":[47],"grid":[48],"game.":[49],"The":[50,151],"designed":[51,138],"method":[52,102,157,165],"can":[53,103,158],"find":[54],"optimal":[56],"solution":[57],"even":[58],"when":[59],"predator":[61],"moves.":[62],"Specifically,":[63],"design":[65],"virtual":[66,89],"agents":[67,90],"interact":[69],"simulated":[71],"changing":[72],"parallel":[75],"instead":[76],"using":[78],"actual":[79,95],"agents.":[80],"Moreover,":[81],"global":[83],"learns":[85],"information":[86],"from":[87],"these":[88],"interacts":[92],"environment":[96],"at":[97],"same":[99],"time.":[100],"This":[101],"not":[104],"only":[105],"effectively":[106],"improve":[107,159],"generalization":[109,170],"performance":[110],"environments,":[116],"but":[117],"also":[118,141],"reduce":[119],"overall":[121],"computational":[122],"cost.":[123],"Two":[124],"simulation":[125],"studies":[126],"considered":[128],"paper":[131],"validate":[133],"effectiveness":[135],"method.":[139],"We":[140],"compare":[142],"results":[144,152],"conventional":[147],"methods.":[150],"indicate":[153],"that":[154],"our":[155],"proposed":[156],"robustness":[161],"contribute":[167],"certain":[172],"extent.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}