{"id":"https://openalex.org/W2978845548","doi":"https://doi.org/10.1109/ijcnn.2019.8851689","title":"RPR-BP: A Deep Reinforcement Learning Method for Automatic Hyperparameter Optimization","display_name":"RPR-BP: A Deep Reinforcement Learning Method for Automatic Hyperparameter Optimization","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2978845548","doi":"https://doi.org/10.1109/ijcnn.2019.8851689","mag":"2978845548"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8851689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5010197223","display_name":"Jia Wu","orcid":"https://orcid.org/0000-0003-0599-0296"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jia WU","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, ChengDu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, ChengDu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078435851","display_name":"SenPeng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"SenPeng CHEN","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, ChengDu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, ChengDu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101751962","display_name":"Xiuyun Chen","orcid":"https://orcid.org/0000-0002-5674-9702"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XiuYun CHEN","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, ChengDu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, ChengDu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010197223"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.4329,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72471376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2019","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9993000030517578,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.995199978351593,"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/hyperparameter","display_name":"Hyperparameter","score":0.8586694002151489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8033026456832886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7543227076530457},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.735081672668457},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6645394563674927},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.548124372959137},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5078769326210022},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.472755491733551},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4720008373260498},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.470630407333374},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.42997556924819946},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.426222026348114},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08797240257263184}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8586694002151489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8033026456832886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7543227076530457},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.735081672668457},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6645394563674927},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.548124372959137},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5078769326210022},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.472755491733551},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4720008373260498},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.470630407333374},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.42997556924819946},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.426222026348114},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08797240257263184},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2019.8851689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"mag:3082289880","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201902248943273359","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W60686164","https://openalex.org/W1522301498","https://openalex.org/W2064675550","https://openalex.org/W2084812512","https://openalex.org/W2097998348","https://openalex.org/W2106411961","https://openalex.org/W2117130368","https://openalex.org/W2119717200","https://openalex.org/W2125186487","https://openalex.org/W2131241448","https://openalex.org/W2133564696","https://openalex.org/W2145339207","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2525778437","https://openalex.org/W2553303224","https://openalex.org/W2766447205","https://openalex.org/W2950182411","https://openalex.org/W2963374479","https://openalex.org/W2964121744","https://openalex.org/W2998768810","https://openalex.org/W6631190155","https://openalex.org/W6671611538","https://openalex.org/W6674385629","https://openalex.org/W6676179485","https://openalex.org/W6678911119","https://openalex.org/W6679434410","https://openalex.org/W6684191040","https://openalex.org/W6727690538","https://openalex.org/W6729956949"],"related_works":["https://openalex.org/W4233965824","https://openalex.org/W2607442583","https://openalex.org/W3199199693","https://openalex.org/W4286970057","https://openalex.org/W4281847915","https://openalex.org/W2995583237","https://openalex.org/W2967237190","https://openalex.org/W4386295066","https://openalex.org/W4323366554","https://openalex.org/W3028852288"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,19,30,42,47,55,111,184,194],"new":[3],"deep":[4],"reinforcement":[5],"learning":[6,16,44,219],"architecture":[7],"-":[8],"RPR-BP":[9],"to":[10,74,86,101,114,188,198],"optimize":[11],"hyperparameter":[12],"for":[13,121],"any":[14],"machine":[15,43,218],"model":[17,45,65],"on":[18,46,66],"given":[20],"data":[21],"set.":[22,49],"In":[23,171],"this":[24,172],"method,":[25],"an":[26],"agent":[27,83,123,137,150,163,182],"constructed":[28],"by":[29,144,153,167,211],"Long":[31],"Short-Term":[32],"Memory":[33],"Network":[34],"aims":[35],"at":[36],"maximizing":[37],"the":[38,61,64,67,71,82,91,94,116,122,125,136,139,145,149,154,158,162,168,181,190,200,203,229],"expected":[39],"accuracy":[40,62],"of":[41,57,63,93,214,243],"validation":[48,68],"At":[50],"each":[51],"iteration,":[52],"it":[53],"selects":[54],"set":[56,69],"hyperparameters":[58,213],"and":[59,99,124,138,179,223,237,247],"uses":[60],"as":[70],"reward":[72,95,155],"signal":[73],"update":[75],"its":[76,88],"internal":[77],"parameters.":[78],"After":[79],"multiple":[80],"iterations,":[81],"learns":[84],"how":[85],"improve":[87],"decisions.":[89],"However,":[90],"computation":[92],"requires":[96],"significant":[97],"time":[98,245],"leads":[100],"low":[102],"sample":[103],"efficiency.":[104],"To":[105],"speed":[106,176],"up":[107,177],"training,":[108],"we":[109,174,192],"employ":[110],"neural":[112],"network":[113,127,141],"predict":[115],"reward.":[117],"The":[118,206],"training":[119,178],"process":[120],"prediction":[126,140,159],"is":[128,151,164],"divided":[129],"into":[130],"three":[131],"phases:":[132],"Real-Predictive-Real":[133],"(RPR).":[134],"First,":[135],"are":[142],"trained":[143,152,165],"real":[146,169],"experience;":[147],"then,":[148],"generated":[156],"from":[157],"network;":[160],"finally,":[161],"again":[166],"experience.":[170],"way,":[173],"can":[175],"make":[180],"achieve":[183],"high":[185],"accuracy.":[186],"Besides,":[187],"reduce":[189],"variance,":[191],"propose":[193],"Bootstrap":[195],"Pool":[196],"(BP)":[197],"guide":[199],"exploration":[201],"in":[202,241],"search":[204],"space.":[205],"experiment":[207],"was":[208],"carried":[209],"out":[210],"optimizing":[212],"two":[215],"widely":[216],"used":[217],"models:":[220],"Random":[221],"Forest":[222],"XGBoost.":[224],"Experimental":[225],"results":[226],"show":[227],"that":[228],"proposed":[230],"method":[231],"outperforms":[232],"random":[233],"search,":[234],"Bayesian":[235],"optimization":[236],"Tree-structured":[238],"Parzen":[239],"Estimator":[240],"terms":[242],"accuracy,":[244],"efficiency":[246],"stability.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}