{"id":"https://openalex.org/W7084078066","doi":"https://doi.org/10.1109/case58245.2025.11164120","title":"Enhancing Counterfactual Data Augmentation for Offline Reinforcement Learning in Vision-Based Control","display_name":"Enhancing Counterfactual Data Augmentation for Offline Reinforcement Learning in Vision-Based Control","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W7084078066","doi":"https://doi.org/10.1109/case58245.2025.11164120"},"language":"en","primary_location":{"id":"doi:10.1109/case58245.2025.11164120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11164120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","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":null,"display_name":"Raffaele Brilli","orcid":null},"institutions":[{"id":"https://openalex.org/I27483092","display_name":"University of Perugia","ror":"https://ror.org/00x27da85","country_code":"IT","type":"education","lineage":["https://openalex.org/I27483092"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Raffaele Brilli","raw_affiliation_strings":["University of Perugia,Department of Engineering,Perugia,06125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Perugia,Department of Engineering,Perugia,06125","institution_ids":["https://openalex.org/I27483092"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Paolo Speziali","orcid":null},"institutions":[{"id":"https://openalex.org/I27483092","display_name":"University of Perugia","ror":"https://ror.org/00x27da85","country_code":"IT","type":"education","lineage":["https://openalex.org/I27483092"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Speziali","raw_affiliation_strings":["University of Perugia,Department of Engineering,Perugia,06125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Perugia,Department of Engineering,Perugia,06125","institution_ids":["https://openalex.org/I27483092"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Alberto Dionigi","orcid":null},"institutions":[{"id":"https://openalex.org/I27483092","display_name":"University of Perugia","ror":"https://ror.org/00x27da85","country_code":"IT","type":"education","lineage":["https://openalex.org/I27483092"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Dionigi","raw_affiliation_strings":["University of Perugia,Department of Engineering,Perugia,06125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Perugia,Department of Engineering,Perugia,06125","institution_ids":["https://openalex.org/I27483092"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Francesco Crocetti","orcid":null},"institutions":[{"id":"https://openalex.org/I27483092","display_name":"University of Perugia","ror":"https://ror.org/00x27da85","country_code":"IT","type":"education","lineage":["https://openalex.org/I27483092"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Crocetti","raw_affiliation_strings":["University of Perugia,Department of Engineering,Perugia,06125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Perugia,Department of Engineering,Perugia,06125","institution_ids":["https://openalex.org/I27483092"]}]},{"author_position":"last","author":{"id":null,"display_name":"Gabriele Costante","orcid":null},"institutions":[{"id":"https://openalex.org/I27483092","display_name":"University of Perugia","ror":"https://ror.org/00x27da85","country_code":"IT","type":"education","lineage":["https://openalex.org/I27483092"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gabriele Costante","raw_affiliation_strings":["University of Perugia,Department of Engineering,Perugia,06125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Perugia,Department of Engineering,Perugia,06125","institution_ids":["https://openalex.org/I27483092"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27483092"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62969665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1417","last_page":"1422"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11711","display_name":"COVID-19 Pandemic Impacts","score":0.16009999811649323,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11711","display_name":"COVID-19 Pandemic Impacts","score":0.16009999811649323,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14087","display_name":"Economic, Educational, Environmental and Organizational Development","score":0.06679999828338623,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14100","display_name":"Scientific Research and Technology","score":0.057500001043081284,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9581000208854675},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7215999960899353},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5008000135421753},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.42669999599456787},{"id":"https://openalex.org/keywords/counterfactual-conditional","display_name":"Counterfactual conditional","score":0.41110000014305115},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4041999876499176},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.38909998536109924}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9581000208854675},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7215999960899353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7175999879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6718000173568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6341999769210815},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.41110000014305115},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.38909998536109924},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.35339999198913574},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26759999990463257}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case58245.2025.11164120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11164120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","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":13,"referenced_works":["https://openalex.org/W2143891888","https://openalex.org/W2158782408","https://openalex.org/W2877093712","https://openalex.org/W2895492910","https://openalex.org/W2962861439","https://openalex.org/W3029901419","https://openalex.org/W3035454705","https://openalex.org/W3150631816","https://openalex.org/W3159890488","https://openalex.org/W3187709298","https://openalex.org/W3204937802","https://openalex.org/W4309028162","https://openalex.org/W4313886663"],"related_works":[],"abstract_inverted_index":{"Offline":[0],"training":[1,67,121],"of":[2,41,132,143],"Deep":[3,97],"Reinforcement":[4],"Learning":[5],"agents":[6],"is":[7,23,36,115],"a":[8,87,141],"valuable":[9],"solution":[10],"for":[11,55,93],"addressing":[12],"autonomous":[13],"control":[14,81,145],"and":[15,26,107,123,150],"robotics":[16],"challenges,":[17],"especially":[18],"when":[19],"acquiring":[20],"real-world":[21],"data":[22,59,90],"particularly":[24,44],"difficult":[25],"simulators":[27],"are":[28],"not":[29],"available.":[30],"Despite":[31],"its":[32,77],"validity,":[33],"this":[34,62],"approach":[35],"burdened":[37],"by":[38,64],"the":[39,66,102,108,120,125,130],"issue":[40,63],"sample":[42],"inefficiency,":[43],"with":[45,69,73,148],"high-dimensional":[46],"data,":[47],"such":[48],"as":[49],"images,":[50],"making":[51],"it":[52],"less":[53],"effective":[54],"vision-based":[56,80,94],"tasks.":[57],"Counterfactual":[58],"augmentation":[60,91],"addresses":[61],"expanding":[65],"dataset":[68,122],"plausible":[70],"samples":[71],"consistent":[72],"stochastic":[74,144],"environments.":[75],"However,":[76],"application":[78],"in":[79],"remains":[82],"underexplored.":[83],"This":[84],"study":[85],"introduces":[86],"novel":[88],"counterfactual":[89],"technique":[92],"tasks,":[95],"leveraging":[96],"Generative":[98],"Models":[99],"to":[100,118,136],"estimate":[101],"Structural":[103],"Causal":[104],"Model":[105],"(SCM)":[106],"associated":[109],"reward":[110],"model.":[111],"The":[112],"learned":[113],"SCM":[114],"then":[116],"used":[117],"augment":[119],"optimize":[124],"DRL":[126],"agents.":[127],"We":[128],"show":[129],"effectiveness":[131],"our":[133],"method":[134],"compared":[135],"existing":[137],"state-of-the-art":[138],"approaches":[139],"on":[140],"series":[142],"problems,":[146],"both":[147],"discrete":[149],"continuous":[151],"action":[152],"spaces.":[153]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}