{"id":"https://openalex.org/W4387642093","doi":"https://doi.org/10.1142/s0218194023500626","title":"A Dual Decision-Making Continuous Reinforcement Learning Method Based on Sim2Real","display_name":"A Dual Decision-Making Continuous Reinforcement Learning Method Based on Sim2Real","publication_year":2023,"publication_date":"2023-10-14","ids":{"openalex":"https://openalex.org/W4387642093","doi":"https://doi.org/10.1142/s0218194023500626"},"language":"en","primary_location":{"id":"doi:10.1142/s0218194023500626","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s0218194023500626","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","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/A5049559324","display_name":"Wenwen Xiao","orcid":"https://orcid.org/0000-0001-9009-0158"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwen Xiao","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai 200444, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0000-0001-9009-0158","affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai 200444, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674034","display_name":"Xinzhi Wang","orcid":"https://orcid.org/0000-0002-4552-3978"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinzhi Wang","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai 200444, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0000-0002-4552-3978","affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai 200444, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426947","display_name":"Xiangfeng Luo","orcid":"https://orcid.org/0000-0003-4577-9241"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangfeng Luo","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai 200444, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0000-0003-4577-9241","affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai 200444, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086702173","display_name":"Shaorong Xie","orcid":"https://orcid.org/0000-0002-8016-9310"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaorong Xie","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai 200444, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0000-0002-8016-9310","affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai 200444, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141962983"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15452122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"03","first_page":"467","last_page":"488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.9790999889373779,"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/T14011","display_name":"Elevator Systems and Control","score":0.9790999889373779,"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":0.97079998254776,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7564707398414612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.637142539024353},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6214478015899658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.460233211517334},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3622795045375824},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.360613077878952}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7564707398414612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.637142539024353},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6214478015899658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.460233211517334},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3622795045375824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.360613077878952},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218194023500626","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s0218194023500626","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G3411408586","display_name":null,"funder_award_id":"61991415.","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":25,"referenced_works":["https://openalex.org/W2087091770","https://openalex.org/W2587838525","https://openalex.org/W2749666028","https://openalex.org/W2984168904","https://openalex.org/W3024507639","https://openalex.org/W3090832832","https://openalex.org/W3092609815","https://openalex.org/W3200806454","https://openalex.org/W3201759799","https://openalex.org/W4210939259","https://openalex.org/W4212979410","https://openalex.org/W4220840735","https://openalex.org/W4224035554","https://openalex.org/W4283815845","https://openalex.org/W4285177584","https://openalex.org/W4292198371","https://openalex.org/W4308985308","https://openalex.org/W4312125978","https://openalex.org/W4317388085","https://openalex.org/W4327949030","https://openalex.org/W4376274293","https://openalex.org/W4381739798","https://openalex.org/W4382237359","https://openalex.org/W4383108265","https://openalex.org/W4386056988"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Continuous":[0],"reinforcement":[1],"learning":[2,40,68,90,139],"carries":[3],"potential":[4],"security":[5],"risks":[6],"when":[7,60],"applied":[8,43],"in":[9,163],"real-world":[10],"scenarios,":[11],"which":[12,107],"could":[13],"have":[14,80],"significant":[15],"societal":[16],"implications.":[17],"While":[18],"its":[19,112],"field":[20],"of":[21,27,70],"application":[22],"is":[23,42,203],"expanding,":[24],"the":[25,67,71,83,104,108,119,155,170,174,197],"majority":[26],"applications":[28],"still":[29,50,204],"remain":[30],"confined":[31],"to":[32,44,91,96,144,153,167,200],"virtual":[33],"environments.":[34,64,98],"If":[35],"only":[36,102],"a":[37,135,150,164,187],"single":[38],"continuous":[39,138],"method":[41,140,148,185],"an":[45],"unmanned":[46,72,109,171],"system,":[47],"it":[48,61],"will":[49,57],"forget":[51],"previously":[52,93],"learned":[53,94],"experiences,":[54],"and":[55,87,114,127,159,196],"retraining":[56],"be":[58],"required":[59],"encounters":[62],"unknown":[63],"This":[65,147],"reduces":[66],"efficiency":[69],"system.":[73],"To":[74],"address":[75],"these":[76,100],"issues,":[77],"some":[78],"scholars":[79],"suggested":[81],"prioritizing":[82],"experience":[84],"playback":[85],"pool":[86],"using":[88],"transfer":[89,199],"apply":[92],"strategies":[95,162],"new":[97],"However,":[99],"methods":[101],"alleviate":[103],"speed":[105],"at":[106],"system":[110,172],"forgets":[111],"experiences":[113],"do":[115],"not":[116],"fundamentally":[117],"solve":[118],"problem.":[120],"Additionally,":[121],"they":[122],"cannot":[123],"prevent":[124],"dangerous":[125],"actions":[126],"falling":[128],"into":[129],"local":[130,156],"optima.":[131],"Therefore,":[132],"we":[133],"propose":[134],"dual":[136],"decision-making":[137],"based":[141],"on":[142],"simulation":[143],"reality":[145],"(Sim2Real).":[146],"employs":[149],"knowledge":[151],"body":[152],"eliminate":[154],"optimal":[157],"dilemma,":[158],"corrects":[160],"bad":[161],"timely":[165],"manner":[166],"ensure":[168],"that":[169,183],"makes":[173],"best":[175],"decision":[176],"every":[177],"time.":[178],"Our":[179],"experimental":[180],"results":[181],"demonstrate":[182],"our":[184],"has":[186],"30%":[188],"higher":[189],"success":[190],"rate":[191],"than":[192],"other":[193],"state-of-the-art":[194],"methods,":[195],"model":[198],"real":[201],"scenes":[202],"highly":[205],"effective.":[206]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}