{"id":"https://openalex.org/W4386380947","doi":"https://doi.org/10.18293/seke2023-053","title":"DDCL: A Dual Decision-making Continuous Reinforcement Learning Method Based on Sim2Real","display_name":"DDCL: A Dual Decision-making Continuous Reinforcement Learning Method Based on Sim2Real","publication_year":2023,"publication_date":"2023-07-01","ids":{"openalex":"https://openalex.org/W4386380947","doi":"https://doi.org/10.18293/seke2023-053"},"language":"en","primary_location":{"id":"doi:10.18293/seke2023-053","is_oa":true,"landing_page_url":"http://doi.org/10.18293/seke2023-053","pdf_url":"https://doi.org/10.18293/seke2023-053","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.18293/seke2023-053","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101567523","display_name":"Wenwen Xiao","orcid":"https://orcid.org/0000-0002-0543-9077"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwen Xiao","raw_affiliation_strings":["School of Computer Engineering and Science","Shanghai University, Shanghai, 200444, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science","institution_ids":[]},{"raw_affiliation_string":"Shanghai University, Shanghai, 200444, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674029","display_name":"Xinzhi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinzhi Wang","raw_affiliation_strings":["School of Computer Engineering and Science","Shanghai University, Shanghai, 200444, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science","institution_ids":[]},{"raw_affiliation_string":"Shanghai University, Shanghai, 200444, China","institution_ids":["https://openalex.org/I113940042"]}]},{"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/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangfeng Luo","raw_affiliation_strings":["School of Computer Engineering and Science","Shanghai University, Shanghai, 200444, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science","institution_ids":[]},{"raw_affiliation_string":"Shanghai University, Shanghai, 200444, China","institution_ids":["https://openalex.org/I113940042"]}]},{"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/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaorong Xie","raw_affiliation_strings":["School of Computer Engineering and Science","Shanghai University, Shanghai, 200444, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science","institution_ids":[]},{"raw_affiliation_string":"Shanghai University, Shanghai, 200444, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086702173"],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10992019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2023","issue":null,"first_page":"20","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.994700014591217,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8284286260604858},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7418541312217712},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.6534124612808228},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6195910573005676},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.564222514629364},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5541391968727112},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5017354488372803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47017163038253784},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46710601449012756},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32846003770828247}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8284286260604858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418541312217712},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.6534124612808228},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6195910573005676},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.564222514629364},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5541391968727112},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5017354488372803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47017163038253784},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46710601449012756},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32846003770828247},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18293/seke2023-053","is_oa":true,"landing_page_url":"http://doi.org/10.18293/seke2023-053","pdf_url":"https://doi.org/10.18293/seke2023-053","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18293/seke2023-053","is_oa":true,"landing_page_url":"http://doi.org/10.18293/seke2023-053","pdf_url":"https://doi.org/10.18293/seke2023-053","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323970","display_name":"Ministry of Industry and Information Technology of the People's Republic of China","ror":"https://ror.org/0385nmy68"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386380947.pdf","grobid_xml":"https://content.openalex.org/works/W4386380947.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2201581102","https://openalex.org/W2587838525","https://openalex.org/W2736601468","https://openalex.org/W2749666028","https://openalex.org/W2781726626","https://openalex.org/W2889987506","https://openalex.org/W2984168904","https://openalex.org/W2996472503","https://openalex.org/W3017160304","https://openalex.org/W3024507639","https://openalex.org/W3034728521","https://openalex.org/W3201759799","https://openalex.org/W4220840735","https://openalex.org/W4285177584","https://openalex.org/W4287814827","https://openalex.org/W6687681856","https://openalex.org/W6733598009","https://openalex.org/W6741002519","https://openalex.org/W6753526802","https://openalex.org/W6778299498"],"related_works":["https://openalex.org/W2081982437","https://openalex.org/W4394857231","https://openalex.org/W2027050655","https://openalex.org/W3028244590","https://openalex.org/W4254349500","https://openalex.org/W2014369232","https://openalex.org/W3122042562","https://openalex.org/W2050078012","https://openalex.org/W2384215291","https://openalex.org/W184839951"],"abstract_inverted_index":{"Continuous":[0],"reinforcement":[1],"learning":[2,38,65,86,132],"carries":[3],"potential":[4],"security":[5],"risks":[6],"when":[7,58],"applied":[8,41],"in":[9,155],"real-world":[10],"scenarios,":[11],"which":[12,102],"could":[13],"have":[14,76],"significant":[15],"societal":[16],"implications.While":[17],"its":[18,107],"field":[19],"of":[20,26,67],"application":[21],"is":[22,40,194],"expanding,":[23],"the":[24,64,68,79,99,103,114,147,162,166,188],"majority":[25],"applications":[27],"still":[28,48,195],"remain":[29],"confined":[30],"to":[31,42,87,92,137,145,159,191],"virtual":[32],"environments.if":[33],"only":[34,97],"a":[35,128,142,156,178],"single":[36],"continuous":[37,131],"method":[39,133,140,176],"an":[43],"unmanned":[44,69,104,163],"system,":[45],"it":[46,59],"will":[47,55],"forget":[49],"previously":[50,89],"learned":[51,90],"experiences,":[52],"and":[53,83,109,121,151,187],"retraining":[54],"be":[56],"required":[57],"encounters":[60],"unknown":[61],"environments.This":[62],"reduces":[63],"efficiency":[66],"system.To":[70],"address":[71],"these":[72,95],"issues,":[73],"some":[74],"scholars":[75],"suggested":[77],"prioritizing":[78],"experience":[80],"playback":[81],"pool":[82],"using":[84],"transfer":[85,190],"apply":[88],"strategies":[91,154],"new":[93],"environments.However,":[94],"methods":[96],"alleviate":[98],"speed":[100],"at":[101],"system":[105,164],"forgets":[106],"experiences":[108],"do":[110],"not":[111],"fundamentally":[112],"solve":[113],"problem.Additionally,":[115],"they":[116],"cannot":[117],"prevent":[118],"dangerous":[119],"actions":[120],"falling":[122],"into":[123],"local":[124,148],"optima.Therefore,":[125],"we":[126],"propose":[127],"dual":[129],"decision-making":[130],"based":[134],"on":[135],"Simulation":[136],"Reality":[138],"(Sim2Real).This":[139],"employs":[141],"knowledge":[143],"body":[144],"eliminate":[146],"optimal":[149],"dilemma,":[150],"corrects":[152],"bad":[153],"timely":[157],"manner":[158],"ensure":[160],"that":[161,174],"makes":[165],"best":[167],"decision":[168],"every":[169],"time.Our":[170],"experimental":[171],"results":[172],"demonstrate":[173],"our":[175],"has":[177],"30%":[179],"higher":[180],"success":[181],"rate":[182],"than":[183],"other":[184],"state-of-the-art":[185],"methods,":[186],"model":[189],"real":[192],"scenes":[193],"highly":[196],"effective.":[197]},"counts_by_year":[],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-10-10T00:00:00"}