{"id":"https://openalex.org/W4404294578","doi":"https://doi.org/10.1109/m2vip62491.2024.10746098","title":"Simulation Diversity: An Approach for Accurate Performance Estimation in Reinforcement Learning","display_name":"Simulation Diversity: An Approach for Accurate Performance Estimation in Reinforcement Learning","publication_year":2024,"publication_date":"2024-10-03","ids":{"openalex":"https://openalex.org/W4404294578","doi":"https://doi.org/10.1109/m2vip62491.2024.10746098"},"language":"en","primary_location":{"id":"doi:10.1109/m2vip62491.2024.10746098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/m2vip62491.2024.10746098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 30th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","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/A5103821849","display_name":"Christopher Carr","orcid":null},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Christopher Carr","raw_affiliation_strings":["Loughborough University,School of AACME,Loughborough,England"],"affiliations":[{"raw_affiliation_string":"Loughborough University,School of AACME,Loughborough,England","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055925493","display_name":"Miguel Mart\u00ednez-Garc\u00eda","orcid":"https://orcid.org/0000-0003-2984-3231"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Miguel Mart\u00ednez-Garc\u00eda","raw_affiliation_strings":["Loughborough University,School of AACME,Loughborough,England"],"affiliations":[{"raw_affiliation_string":"Loughborough University,School of AACME,Loughborough,England","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022924212","display_name":"Enyan Zhang","orcid":"https://orcid.org/0009-0002-3006-6601"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eve Zhang","raw_affiliation_strings":["Loughborough University,School of AACME,Loughborough,England"],"affiliations":[{"raw_affiliation_string":"Loughborough University,School of AACME,Loughborough,England","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013053105","display_name":"Matthew Coombes","orcid":"https://orcid.org/0000-0002-4421-9464"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthew Coombes","raw_affiliation_strings":["Loughborough University,School of AACME,Loughborough,England"],"affiliations":[{"raw_affiliation_string":"Loughborough University,School of AACME,Loughborough,England","institution_ids":["https://openalex.org/I143804889"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103821849"],"corresponding_institution_ids":["https://openalex.org/I143804889"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17638454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7674000263214111,"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":0.7674000263214111,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.7311000227928162,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.6488999724388123,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7552971839904785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6962623596191406},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.6401177644729614},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5120552182197571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42319053411483765},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40638822317123413},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1392638087272644},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06834679841995239}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7552971839904785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6962623596191406},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.6401177644729614},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5120552182197571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42319053411483765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40638822317123413},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1392638087272644},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06834679841995239},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/m2vip62491.2024.10746098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/m2vip62491.2024.10746098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 30th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2028893450","https://openalex.org/W2465948386","https://openalex.org/W2564095182","https://openalex.org/W2736601468","https://openalex.org/W2769498435","https://openalex.org/W2809668646","https://openalex.org/W2962688977","https://openalex.org/W2964248288","https://openalex.org/W2968800739","https://openalex.org/W2982095652","https://openalex.org/W2997480594","https://openalex.org/W3088310808","https://openalex.org/W3102552342","https://openalex.org/W3120778962","https://openalex.org/W3161634385","https://openalex.org/W3177014898","https://openalex.org/W3187993326","https://openalex.org/W3201824844","https://openalex.org/W4295549420","https://openalex.org/W4312309366","https://openalex.org/W4315487473","https://openalex.org/W4386285856","https://openalex.org/W4390872389","https://openalex.org/W6734129231","https://openalex.org/W6741002519","https://openalex.org/W6746335678","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6752431149","https://openalex.org/W6756840741","https://openalex.org/W6766956246","https://openalex.org/W6780559895","https://openalex.org/W6782364735","https://openalex.org/W6801872694","https://openalex.org/W6841586102"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"In":[0],"the":[1,7,22,41,69,88,118,122,130,133,152,160],"realm":[2],"of":[3,43,59,71,87,91,106,117,148,155],"Reinforcement":[4],"Learning":[5],"research,":[6],"Sim-to-Real":[8],"(S2R)":[9],"gap":[10,16],"poses":[11],"a":[12,19,50,113,142,156],"persistent":[13],"challenge.":[14],"This":[15],"manifests":[17],"as":[18],"decline":[20],"in":[21,25,28,40,93,159],"agent\u2019s":[23],"performance":[24,72,150,154],"real-world":[26,95],"scenarios":[27],"contrast":[29],"to":[30,45,63],"simulations.":[31],"Addressing":[32],"this":[33],"issue":[34],"is":[35,101,112],"crucial":[36],"for":[37],"enhancing":[38,68],"decision-making":[39],"deployment":[42],"agents":[44],"reality.":[46],"Therefore,":[47],"we":[48],"propose":[49],"novel":[51],"technique,":[52],"named":[53],"Simulation":[54],"Diversity":[55],"(SD),":[56],"which":[57],"consists":[58],"employing":[60],"multiple":[61],"simulators":[62],"articulate":[64],"similar":[65],"dynamics,":[66],"thereby":[67],"accuracy":[70,135],"estimation.":[73],"Quantitative":[74],"metrics,":[75],"including":[76],"Wasserstein":[77],"Distance,":[78,80],"Energy":[79],"and":[81,151],"Mean":[82],"Squared":[83],"Error":[84],"provide":[85],"evidence":[86],"improved":[89],"capabilities":[90],"SD":[92,111],"mimicking":[94],"agent":[96,149],"performance.":[97],"The":[98,124],"proposed":[99],"approach":[100],"further":[102],"validated":[103],"by":[104,121,137],"way":[105],"micro-accuracy":[107],"assessments,":[108],"showcasing":[109],"that":[110],"much":[114],"better":[115],"predictor":[116],"reward":[119],"gained":[120],"agent.":[123],"paper":[125],"provides":[126],"valuable":[127],"insights":[128],"into":[129],"rationale":[131],"behind":[132],"increased":[134],"achieved":[136],"SD.":[138],"Experimental":[139],"results":[140],"demonstrate":[141],"comparative":[143],"analysis":[144],"between":[145],"simulator-based":[146],"estimations":[147],"actual":[153],"deployed":[157],"policy":[158],"real":[161],"world.":[162]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}