{"id":"https://openalex.org/W4317038468","doi":"https://doi.org/10.1109/tii.2022.3232774","title":"Hand-in-Hand Guidance: An Explore-Exploit Based Reinforcement Learning Method for Performance Driven Assembly-Adjustment","display_name":"Hand-in-Hand Guidance: An Explore-Exploit Based Reinforcement Learning Method for Performance Driven Assembly-Adjustment","publication_year":2023,"publication_date":"2023-01-17","ids":{"openalex":"https://openalex.org/W4317038468","doi":"https://doi.org/10.1109/tii.2022.3232774"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2022.3232774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2022.3232774","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","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/A5083331685","display_name":"Guifang Duan","orcid":"https://orcid.org/0000-0001-7974-7059"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guifang Duan","raw_affiliation_strings":["State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103143732","display_name":"Yunkun Xu","orcid":"https://orcid.org/0000-0002-8698-0075"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunkun Xu","raw_affiliation_strings":["State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China","Huawei Cloud, Guian, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Huawei Cloud, Guian, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405185","display_name":"Zhenyu Liu","orcid":"https://orcid.org/0000-0003-2463-4553"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Liu","raw_affiliation_strings":["State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039962474","display_name":"Jianrong Tan","orcid":"https://orcid.org/0000-0002-7425-341X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianrong Tan","raw_affiliation_strings":["State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083331685"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.7315,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68750667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"19","issue":"10","first_page":"10045","last_page":"10055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9905999898910522,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.9686999917030334,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/exploit","display_name":"Exploit","score":0.7654678821563721},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7532057762145996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7418681383132935},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6383100748062134},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.5498988628387451},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5366135835647583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5312934517860413},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.511480450630188},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.50285404920578},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4895247220993042}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7654678821563721},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7532057762145996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418681383132935},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6383100748062134},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.5498988628387451},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5366135835647583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5312934517860413},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.511480450630188},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.50285404920578},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4895247220993042},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2022.3232774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2022.3232774","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5385680445","display_name":null,"funder_award_id":"52075480","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1976799371","https://openalex.org/W2050412635","https://openalex.org/W2145339207","https://openalex.org/W2679717297","https://openalex.org/W2736601468","https://openalex.org/W2736629007","https://openalex.org/W2737802181","https://openalex.org/W2743151379","https://openalex.org/W2781726626","https://openalex.org/W2890090623","https://openalex.org/W2891186800","https://openalex.org/W2908251145","https://openalex.org/W2964067469","https://openalex.org/W2966352676","https://openalex.org/W2990681646","https://openalex.org/W2995429865","https://openalex.org/W3012544020","https://openalex.org/W3018036994","https://openalex.org/W3034956653","https://openalex.org/W3088121331","https://openalex.org/W3101781665","https://openalex.org/W3113190209","https://openalex.org/W3129322645","https://openalex.org/W3156399319","https://openalex.org/W3204987448","https://openalex.org/W3210326730","https://openalex.org/W6627932998","https://openalex.org/W6683397050","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6756303580","https://openalex.org/W6769580333","https://openalex.org/W6775522024","https://openalex.org/W6775683342","https://openalex.org/W6787998924","https://openalex.org/W6803213246"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2264067234","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Nowadays,":[0],"most":[1],"high-precision":[2],"products":[3,23],"are":[4,100],"still":[5],"assembled":[6],"manually,":[7],"which":[8],"leads":[9],"to":[10,20,46,56,75,81,105,137,151,167],"a":[11,72,87,127,191],"low":[12],"one-time":[13],"pass":[14],"rate":[15],"of":[16,120,129,143,194],"products.":[17,84],"Workers":[18],"need":[19,55],"adjust":[21,57,82],"unqualified":[22,83,147],"repeatedly":[24],"based":[25],"on":[26,185],"experience,":[27],"resulting":[28],"in":[29,79,112,170],"inefficiency":[30],"and":[31,51,93,177,190],"poor":[32],"quality":[33],"consistency.":[34],"In":[35,96],"this":[36],"work,":[37],"we":[38],"propose":[39],"an":[40,139,186],"explore-exploit":[41],"reinforcement":[42],"learning":[43,89,163],"(EERL)":[44],"framework":[45],"suggest":[47],"the":[48,63,103,108,113,133,152,158,171,195,202],"assembly":[49,110,149],"parameters":[50],"quantity":[52],"that":[53,201],"workers":[54,77],"at":[58],"each":[59],"step.":[60],"Jointed":[61],"with":[62,174],"pretrained":[64],"product":[65],"performance":[66],"prediction":[67],"model,":[68],"EERL":[69,85],"can":[70],"output":[71],"sequential":[73],"decision":[74],"guide":[76],"hand":[78,80],"includes":[86],"two-phase":[88],"process:":[90],"1)":[91],"exploration;":[92],"2)":[94],"exploitation.":[95],"exploration":[97],"phase,":[98],"agents":[99],"encouraged":[101],"by":[102],"curiosity":[104],"fully":[106],"explore":[107],"qualified":[109,154],"states":[111],"assembly-adjustment":[114,140,159],"feature":[115],"space.":[116],"The":[117,161,180,197],"regulated":[118],"difference":[119],"random":[121],"network":[122],"distillation":[123],"is":[124,135,165,183],"used":[125],"as":[126],"measure":[128],"curiosity.":[130],"During":[131],"exploitation,":[132],"agent":[134],"trained":[136],"learn":[138,168],"guidance":[141],"policy":[142],"moving":[144],"from":[145],"any":[146],"initial":[148],"state":[150,155],"corresponding":[153],"while":[156],"satisfying":[157],"constraints.":[160,179],"curriculum":[162],"mechanism":[164],"introduced":[166],"effectively":[169],"complex":[172],"environment":[173],"sparse":[175],"reward":[176],"adjustment":[178],"proposed":[181,203],"approach":[182,204],"validated":[184],"benchmark":[187],"optimization":[188],"function":[189],"case":[192],"study":[193],"gyroscope.":[196],"experimental":[198],"results":[199],"demonstrate":[200],"outperforms":[205],"other":[206],"existing":[207],"approaches.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}