{"id":"https://openalex.org/W3081678145","doi":"https://doi.org/10.1109/tnnls.2020.3008249","title":"Intelligent Trainer for Dyna-Style Model-Based Deep Reinforcement Learning","display_name":"Intelligent Trainer for Dyna-Style Model-Based Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-08-31","ids":{"openalex":"https://openalex.org/W3081678145","doi":"https://doi.org/10.1109/tnnls.2020.3008249","mag":"3081678145","pmid":"https://pubmed.ncbi.nlm.nih.gov/32866102"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.3008249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3008249","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5020197760","display_name":"Linsen Dong","orcid":"https://orcid.org/0000-0002-0315-1125"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Linsen Dong","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0315-1125","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648806","display_name":"Yuanlong Li","orcid":"https://orcid.org/0000-0002-2375-1806"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuanlong Li","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2375-1806","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007633349","display_name":"Xin Zhou","orcid":"https://orcid.org/0000-0001-5405-9890"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xin Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041572550","display_name":"Yonggang Wen","orcid":"https://orcid.org/0000-0002-2751-5114"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yonggang Wen","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2751-5114","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111470708","display_name":"Kyle Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Guan","raw_affiliation_strings":["Nokia Bell Labs, Holmdel, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Holmdel, NJ, USA","institution_ids":["https://openalex.org/I72090969"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.268,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.84544778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"32","issue":"6","first_page":"2758","last_page":"2771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9995999932289124,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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/T14011","display_name":"Elevator Systems and Control","score":0.9283999800682068,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/trainer","display_name":"Trainer","score":0.856972336769104},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7240793108940125},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6475648880004883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6220735311508179},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48807990550994873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4014231264591217},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33397993445396423},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17693695425987244},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.11225831508636475}],"concepts":[{"id":"https://openalex.org/C2780463512","wikidata":"https://www.wikidata.org/wiki/Q15122700","display_name":"Trainer","level":2,"score":0.856972336769104},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7240793108940125},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6475648880004883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6220735311508179},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48807990550994873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4014231264591217},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33397993445396423},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17693695425987244},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.11225831508636475},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2020.3008249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3008249","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:32866102","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32866102","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:dr.ntu.edu.sg:10356/159633","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/159633","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1863261251","display_name":null,"funder_award_id":"BSEWWT2017_2_06","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G2945503839","display_name":null,"funder_award_id":"NRF2017EWT-EP003-023","funder_id":"https://openalex.org/F4320320743","funder_display_name":"Energy Market Authority of Singapore"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320743","display_name":"Energy Market Authority of Singapore","ror":"https://ror.org/05tqbd879"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W560518094","https://openalex.org/W1515308897","https://openalex.org/W1520597402","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1804641549","https://openalex.org/W1980035368","https://openalex.org/W2012451615","https://openalex.org/W2035003264","https://openalex.org/W2048687352","https://openalex.org/W2060605484","https://openalex.org/W2091565802","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2126909264","https://openalex.org/W2140135625","https://openalex.org/W2168342951","https://openalex.org/W2257979135","https://openalex.org/W2280163991","https://openalex.org/W2319954399","https://openalex.org/W2343701426","https://openalex.org/W2344786740","https://openalex.org/W2475651303","https://openalex.org/W2586798638","https://openalex.org/W2604726708","https://openalex.org/W2738669288","https://openalex.org/W2738675347","https://openalex.org/W2742454413","https://openalex.org/W2774354230","https://openalex.org/W2785389871","https://openalex.org/W2884970059","https://openalex.org/W2885245712","https://openalex.org/W2886851211","https://openalex.org/W2899639849","https://openalex.org/W2949571867","https://openalex.org/W2962872206","https://openalex.org/W2963616477","https://openalex.org/W2963864421","https://openalex.org/W2964229770","https://openalex.org/W2964295739","https://openalex.org/W3037207827","https://openalex.org/W4214717370","https://openalex.org/W4293396018","https://openalex.org/W4294336468","https://openalex.org/W4297729342","https://openalex.org/W4298857966","https://openalex.org/W6630899555","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6680657880","https://openalex.org/W6684921986","https://openalex.org/W6691861496","https://openalex.org/W6695011786","https://openalex.org/W6733053627","https://openalex.org/W6736742618","https://openalex.org/W6741940250","https://openalex.org/W6746581380","https://openalex.org/W6748519856","https://openalex.org/W6751087324","https://openalex.org/W6754471908","https://openalex.org/W6754993503","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W1866966336","https://openalex.org/W4388176369","https://openalex.org/W1985489398","https://openalex.org/W638029546","https://openalex.org/W4285792946","https://openalex.org/W2920061524","https://openalex.org/W2000494260","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W154293939"],"abstract_inverted_index":{"Model-based":[0],"reinforcement":[1],"learning":[2,53],"(MBRL)":[3],"has":[4],"been":[5],"proposed":[6,181,200,228],"as":[7,113,127],"a":[8,25,84,114,177,205],"promising":[9],"alternative":[10,168],"solution":[11],"to":[12,29,90,134,150,156,213,235],"tackle":[13],"the":[14,20,45,68,92,105,141,158,190,221],"high":[15],"sampling":[16,57,216],"cost":[17,217],"challenge":[18],"in":[19,189,208,225],"canonical":[21,106],"RL,":[22],"by":[23,44,63],"leveraging":[24],"system":[26,54],"dynamics":[27],"model":[28],"generate":[30],"synthetic":[31],"data":[32,58],"for":[33,140,186],"policy":[34],"training":[35,69,108,119],"purpose.":[36],"The":[37,101,123,227],"MBRL":[38,107],"framework,":[39],"nevertheless,":[40],"is":[41,76,104,111,184],"inherently":[42],"limited":[43],"convoluted":[46,93],"process":[47,70,109,120],"of":[48,99],"jointly":[49],"optimizing":[50],"control":[51],"policy,":[52],"dynamics,":[55],"and":[56,75,165,175],"from":[59],"two":[60,96,167],"sources":[61],"controlled":[62],"complicated":[64],"hyperparameters.":[65],"As":[66],"such,":[67],"involves":[71],"overwhelmingly":[72],"manual":[73],"tuning":[74],"prohibitively":[77],"costly.":[78],"In":[79,160],"this":[80],"research,":[81,162],"we":[82,163],"propose":[83,164],"\"reinforcement":[85],"on":[86],"reinforcement\"":[87],"(RoR)":[88],"architecture":[89],"decompose":[91],"tasks":[94,188,236],"into":[95],"decoupled":[97],"layers":[98],"RL.":[100],"inner":[102,142],"layer":[103,125],"which":[110],"formulated":[112],"Markov":[115],"decision":[116],"process,":[117],"called":[118,131],"environment":[121],"(TPE).":[122],"outer":[124],"serves":[126],"an":[128,136,172],"RL":[129],"agent,":[130],"intelligent":[132,201],"trainer,":[133],"learn":[135],"optimal":[137],"hyperparameter":[138,240],"configuration":[139],"TPE.":[143],"This":[144],"decomposition":[145],"approach":[146],"provides":[147],"much-needed":[148],"flexibility":[149],"implement":[151],"different":[152],"trainer":[153,169,174,202,229],"designs,":[154],"referred":[155],"\"train":[157],"trainer.\"":[159],"our":[161,199],"optimize":[166],"designs:":[170],"1)":[171],"unihead":[173],"2)":[176],"multihead":[178],"trainer.":[179],"Our":[180],"RoR":[182],"framework":[183,230],"evaluated":[185],"five":[187],"OpenAI":[191],"gym.":[192],"Compared":[193],"with":[194,211],"three":[195],"other":[196],"baseline":[197],"methods,":[198],"methods":[203],"have":[204],"competitive":[206],"performance":[207],"autotuning":[209],"capability,":[210],"up":[212],"56%":[214],"expected":[215],"saving":[218],"without":[219],"knowing":[220],"best":[222],"parameter":[223],"configurations":[224],"advance.":[226],"can":[231],"be":[232],"easily":[233],"extended":[234],"that":[237],"require":[238],"costly":[239],"tuning.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}