{"id":"https://openalex.org/W3215847557","doi":"https://doi.org/10.1109/ssci50451.2021.9660006","title":"Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning","display_name":"Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning","publication_year":2021,"publication_date":"2021-12-05","ids":{"openalex":"https://openalex.org/W3215847557","doi":"https://doi.org/10.1109/ssci50451.2021.9660006","mag":"3215847557"},"language":"en","primary_location":{"id":"doi:10.1109/ssci50451.2021.9660006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9660006","pdf_url":null,"source":{"id":"https://openalex.org/S4363604921","display_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5005487112","display_name":"Phillip Swazinna","orcid":"https://orcid.org/0000-0003-4667-9584"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Phillip Swazinna","raw_affiliation_strings":["Siemens Technology & Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Technology & Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I1325886976","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035246650","display_name":"Steffen Udluft","orcid":"https://orcid.org/0000-0002-5767-2591"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Udluft","raw_affiliation_strings":["Siemens Technology, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Technology, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002518694","display_name":"Thomas A. Runkler","orcid":"https://orcid.org/0000-0002-5465-198X"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Runkler","raw_affiliation_strings":["Siemens Technology & Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Technology & Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I1325886976","https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3804,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.60203327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9815999865531921,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9555000066757202,"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":0.841919481754303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8076986074447632},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6668102145195007},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.6605571508407593},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6290647983551025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6286696791648865},{"id":"https://openalex.org/keywords/simplicity","display_name":"Simplicity","score":0.5889874696731567},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5244465470314026},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.42765533924102783},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.42125535011291504},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39152657985687256},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.14651721715927124},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08838838338851929}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.841919481754303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076986074447632},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6668102145195007},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.6605571508407593},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6290647983551025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6286696791648865},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.5889874696731567},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5244465470314026},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.42765533924102783},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.42125535011291504},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39152657985687256},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.14651721715927124},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08838838338851929},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci50451.2021.9660006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9660006","pdf_url":null,"source":{"id":"https://openalex.org/S4363604921","display_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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":82,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W2004291985","https://openalex.org/W2034334856","https://openalex.org/W2108598243","https://openalex.org/W2125943921","https://openalex.org/W2173248099","https://openalex.org/W2212660284","https://openalex.org/W2396820603","https://openalex.org/W2437617937","https://openalex.org/W2736601468","https://openalex.org/W2760661167","https://openalex.org/W2762776810","https://openalex.org/W2781726626","https://openalex.org/W2904453761","https://openalex.org/W2928125049","https://openalex.org/W2946595616","https://openalex.org/W2947150733","https://openalex.org/W2949608212","https://openalex.org/W2962735385","https://openalex.org/W2963704132","https://openalex.org/W2963864421","https://openalex.org/W2963982883","https://openalex.org/W2968778390","https://openalex.org/W2991355586","https://openalex.org/W3016525976","https://openalex.org/W3017362854","https://openalex.org/W3025606523","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3033691439","https://openalex.org/W3037024314","https://openalex.org/W3037440645","https://openalex.org/W3038233649","https://openalex.org/W3043057128","https://openalex.org/W3043128363","https://openalex.org/W3048825312","https://openalex.org/W3096964654","https://openalex.org/W3099427826","https://openalex.org/W3123216837","https://openalex.org/W3128328080","https://openalex.org/W3129049248","https://openalex.org/W3130177876","https://openalex.org/W3149723172","https://openalex.org/W3173205304","https://openalex.org/W3175311658","https://openalex.org/W3178225342","https://openalex.org/W3201700917","https://openalex.org/W3207240768","https://openalex.org/W4287631403","https://openalex.org/W4287689949","https://openalex.org/W4287714048","https://openalex.org/W4298857966","https://openalex.org/W4300485191","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6684921986","https://openalex.org/W6688325169","https://openalex.org/W6713841817","https://openalex.org/W6741002519","https://openalex.org/W6744893653","https://openalex.org/W6747473740","https://openalex.org/W6757469721","https://openalex.org/W6763088532","https://openalex.org/W6763704811","https://openalex.org/W6771270455","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6779562500","https://openalex.org/W6779733183","https://openalex.org/W6780159193","https://openalex.org/W6781272356","https://openalex.org/W6782145165","https://openalex.org/W6785193213","https://openalex.org/W6790767801","https://openalex.org/W6791413555","https://openalex.org/W6793827024","https://openalex.org/W6797518001","https://openalex.org/W6840678999","https://openalex.org/W7036772505"],"related_works":["https://openalex.org/W2368019753","https://openalex.org/W2333930193","https://openalex.org/W4210711561","https://openalex.org/W4225619808","https://openalex.org/W4400438570","https://openalex.org/W4376223516","https://openalex.org/W4226042081","https://openalex.org/W4388926065","https://openalex.org/W4308935744","https://openalex.org/W4362599051"],"abstract_inverted_index":{"Recently":[0],"developed":[1],"offline":[2],"reinforcement":[3],"learning":[4],"algorithms":[5,29],"have":[6],"made":[7],"it":[8],"possible":[9],"to":[10,19,32,42,46,71],"learn":[11],"policies":[12],"directly":[13],"from":[14],"pre-collected":[15],"datasets,":[16],"giving":[17],"rise":[18],"a":[20,94],"new":[21],"dilemma":[22],"for":[23,113],"practitioners:":[24],"Since":[25],"the":[26,28,37,48,52,64,97],"performance":[27],"are":[30],"able":[31],"deliver":[33],"depends":[34],"greatly":[35],"on":[36],"dataset":[38,50,114],"that":[39,103],"is":[40],"presented":[41],"them,":[43],"practitioners":[44],"need":[45],"pick":[47],"right":[49],"among":[51],"available":[53],"ones.":[54],"This":[55],"problem":[56],"has":[57],"so":[58],"far":[59],"not":[60],"been":[61],"discussed":[62],"in":[63],"corresponding":[65],"literature.":[66],"We":[67],"discuss":[68],"ideas":[69],"how":[70],"select":[72],"promising":[73],"datasets":[74],"and":[75,86,100],"propose":[76],"three":[77],"very":[78,110],"simple":[79],"indicators:":[80],"Estimated":[81],"relative":[82],"return":[83],"improvement":[84],"(ERI)":[85],"estimated":[87],"action":[88],"stochasticity":[89],"(EAS),":[90],"as":[91,93],"well":[92],"combination":[95],"of":[96],"two":[98],"(COI),":[99],"empirically":[101],"show":[102],"despite":[104],"their":[105],"simplicity":[106],"they":[107],"can":[108],"be":[109],"effectively":[111],"used":[112],"selection.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-30T13:55:48.251075","created_date":"2025-10-10T00:00:00"}