{"id":"https://openalex.org/W2956156147","doi":"https://doi.org/10.3233/jifs-190209","title":"Particle swarm optimization based multi-task parallel reinforcementlearning algorithm","display_name":"Particle swarm optimization based multi-task parallel reinforcementlearning algorithm","publication_year":2019,"publication_date":"2019-07-03","ids":{"openalex":"https://openalex.org/W2956156147","doi":"https://doi.org/10.3233/jifs-190209","mag":"2956156147"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-190209","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-190209","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy 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/A5065976386","display_name":"Duan Junhua","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Duan Junhua","raw_affiliation_strings":["School of Computer, Northwestern Polytechnical University, Beilin District, Xi\u2019an Shaanxi, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Northwestern Polytechnical University, Beilin District, Xi\u2019an Shaanxi, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006814445","display_name":"Yian Zhu","orcid":"https://orcid.org/0000-0001-6564-5756"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhu Yi-an","raw_affiliation_strings":["School of Computer, Northwestern Polytechnical University, Beilin District, Xi\u2019an Shaanxi, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Northwestern Polytechnical University, Beilin District, Xi\u2019an Shaanxi, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101808392","display_name":"Zhong Dong","orcid":"https://orcid.org/0000-0001-9970-6510"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Dong","raw_affiliation_strings":["School of Computer, Northwestern Polytechnical University, Beilin District, Xi\u2019an Shaanxi, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Northwestern Polytechnical University, Beilin District, Xi\u2019an Shaanxi, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633246","display_name":"Lixiang Zhang","orcid":"https://orcid.org/0000-0003-4075-6999"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Lixiang","raw_affiliation_strings":["School of Computer, Northwestern Polytechnical University, Beilin District, Xi\u2019an Shaanxi, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Northwestern Polytechnical University, Beilin District, Xi\u2019an Shaanxi, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351849","display_name":"Lin Zhang","orcid":"https://orcid.org/0000-0002-4360-5523"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Lin","raw_affiliation_strings":["School of Computer, Northwestern Polytechnical University, Beilin District, Xi\u2019an Shaanxi, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Northwestern Polytechnical University, Beilin District, Xi\u2019an Shaanxi, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006814445"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64804559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"37","issue":"6","first_page":"8567","last_page":"8575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9961000084877014,"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":0.9961000084877014,"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":0.9883000254631042,"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/T12676","display_name":"Machine Learning and ELM","score":0.967199981212616,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.764288067817688},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7351643443107605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6360719203948975},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.603662371635437},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5760184526443481},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.53836989402771},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5277372598648071},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5239622592926025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5210777521133423},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.48734626173973083},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.4572962522506714},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.45676377415657043},{"id":"https://openalex.org/keywords/online-machine-learning","display_name":"Online machine learning","score":0.4486171007156372},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44680726528167725},{"id":"https://openalex.org/keywords/instance-based-learning","display_name":"Instance-based learning","score":0.4282833933830261},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4261653423309326},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2245945930480957},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0576343834400177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.764288067817688},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7351643443107605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6360719203948975},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.603662371635437},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5760184526443481},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.53836989402771},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5277372598648071},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5239622592926025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5210777521133423},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.48734626173973083},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.4572962522506714},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.45676377415657043},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.4486171007156372},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44680726528167725},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.4282833933830261},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4261653423309326},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2245945930480957},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0576343834400177},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-190209","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-190209","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W605348272","https://openalex.org/W1974043469","https://openalex.org/W2509607449","https://openalex.org/W2575472443","https://openalex.org/W2580909119","https://openalex.org/W2608176893","https://openalex.org/W2754926205","https://openalex.org/W2766258251","https://openalex.org/W2896823681","https://openalex.org/W2917089854","https://openalex.org/W2923653485","https://openalex.org/W2939569248","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3196155444","https://openalex.org/W4319309271","https://openalex.org/W2806899865","https://openalex.org/W3136151706","https://openalex.org/W3208584567","https://openalex.org/W3047894882","https://openalex.org/W4366320140","https://openalex.org/W4285160008","https://openalex.org/W4320063314","https://openalex.org/W3140225428"],"abstract_inverted_index":{"Transfer":[0],"learning":[1,13,22,50,54,58,65,122,133,176,183,196,211,220],"has":[2],"been":[3],"identified":[4],"as":[5],"conducive":[6],"to":[7,77,80,100,117,234],"improving":[8],"the":[9,25,44,53,61,64,67,73,81,92,96,101,110,148,153,169,181,185,202,206,209,225,228],"speed":[10,55,94],"of":[11,27,56,66,86,95,112,150,205,227],"machine":[12],"in":[14,35,123,201,232],"many":[15],"areas.":[16],"In":[17,127,180,208],"multi-task":[18,47,124,132],"reinforcement":[19,97,173],"learning,":[20,174],"transfer":[21,26,49],"can":[23,51,71,89,222],"assist":[24],"experiences":[28],"between":[29],"different":[30],"tasks.":[31,59],"The":[32,84,218],"research":[33,102],"conducted":[34,199],"this":[36,87,107,128],"article":[37],"is":[38,144,178,190,198,215],"focused":[39],"on":[40,142,147,168],"two":[41,105],"aspects.":[42],"On":[43,60],"one":[45],"hand,":[46,63],"parallel":[48,57,125],"improve":[52],"other":[62],"current":[68],"optimal":[69],"experience":[70],"help":[72,223],"target":[74],"point":[75],"rewards":[76],"be":[78],"transmitted":[79],"starting":[82],"point.":[83],"value":[85],"self-learning":[88,119],"also":[90],"accelerate":[91],"convergence":[93],"learning.":[98,126,207],"According":[99],"into":[103],"these":[104],"aspects,":[106],"paper":[108],"uses":[109],"idea":[111,149],"particle":[113],"swarm":[114],"optimization":[115],"(PSO)":[116],"conduct":[118],"and":[120,159,192,230],"interactive":[121],"paper,":[129],"a":[130],"new":[131],"algorithm":[134],"named":[135],"PSO-MTPRL":[136],"(Multi-Task":[137],"Parallel":[138],"Reinforcement":[139],"Learning":[140,161],"based":[141],"PSO)":[143],"proposed.":[145],"Based":[146,167],"PSO":[151],"algorithm,":[152],"Boltzmann":[154,187,213],"strategy,":[155],"Self-Learning":[156],"Process":[157,162],"(SLP)":[158],"Interactive":[160],"(ILP)":[163],"are":[164],"selected":[165],"probabilistically.":[166],"characteristic":[170],"exhibited":[171],"by":[172],"segmented":[175,219],"model":[177,221],"recommended.":[179],"early":[182],"stages,":[184,212],"complete":[186],"exploration":[188,214,229],"strategy":[189],"applied,":[191],"B-SLP-ILP":[193],"(Boltzmann-SLP-":[194],"ILP)":[195],"procedure":[197],"exclusively":[200],"middle":[203],"stage":[204],"late":[210],"involved":[216],"again.":[217],"ensure":[224],"balance":[226],"exploitation,":[231],"addition":[233],"ensuring":[235],"that":[236],"all":[237],"tasks":[238],"convergence.":[239]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}