{"id":"https://openalex.org/W4388017139","doi":"https://doi.org/10.2478/jaiscr-2023-0019","title":"Discrete Uncertainty Quantification For Offline Reinforcement Learning","display_name":"Discrete Uncertainty Quantification For Offline Reinforcement Learning","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4388017139","doi":"https://doi.org/10.2478/jaiscr-2023-0019"},"language":"en","primary_location":{"id":"doi:10.2478/jaiscr-2023-0019","is_oa":true,"landing_page_url":"https://doi.org/10.2478/jaiscr-2023-0019","pdf_url":"https://sciendo.com/pdf/10.2478/jaiscr-2023-0019","source":{"id":"https://openalex.org/S4210223945","display_name":"Journal of Artificial Intelligence and Soft Computing Research","issn_l":"2083-2567","issn":["2083-2567","2449-6499"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317241","host_organization_name":"Polish Neural Network Society, the University of Social Sciences in Lodz & Czestochowa University of Technology","host_organization_lineage":["https://openalex.org/P4310317241"],"host_organization_lineage_names":["Polish Neural Network Society, the University of Social Sciences in Lodz & Czestochowa University of Technology"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence and Soft Computing Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://sciendo.com/pdf/10.2478/jaiscr-2023-0019","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101492976","display_name":"Jos\u00e9 Luis P\u00e9rez","orcid":"https://orcid.org/0009-0002-8623-3595"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Luis P\u00e9rez","raw_affiliation_strings":["Computer Science Department , Universidad Carlos III de Madrid , Spain"],"raw_orcid":"https://orcid.org/0009-0002-8623-3595","affiliations":[{"raw_affiliation_string":"Computer Science Department , Universidad Carlos III de Madrid , Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052972093","display_name":"Javier Corrochano","orcid":"https://orcid.org/0000-0003-3687-700X"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Corrochano","raw_affiliation_strings":["Computer Science Department , Universidad Carlos III de Madrid , Spain"],"raw_orcid":"https://orcid.org/0000-0003-3687-700X","affiliations":[{"raw_affiliation_string":"Computer Science Department , Universidad Carlos III de Madrid , Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645872","display_name":"Javier Garc\u00eda","orcid":"https://orcid.org/0000-0002-5638-5240"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Garc\u00eda","raw_affiliation_strings":["Electronics and Computing Department , Universidad de Santiago de Compostela , Spain"],"raw_orcid":"https://orcid.org/0000-0002-5638-5240","affiliations":[{"raw_affiliation_string":"Electronics and Computing Department , Universidad de Santiago de Compostela , Spain","institution_ids":["https://openalex.org/I200284239"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043408401","display_name":"Rub\u00e9n Majadas","orcid":"https://orcid.org/0000-0002-3395-7330"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Rub\u00e9n Majadas","raw_affiliation_strings":["Computer Science Department , Universidad Carlos III de Madrid , Spain"],"raw_orcid":"https://orcid.org/0000-0002-3395-7330","affiliations":[{"raw_affiliation_string":"Computer Science Department , Universidad Carlos III de Madrid , Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021352012","display_name":"Cristina Iba\u00f1ez-Llano","orcid":"https://orcid.org/0009-0003-1917-3382"},"institutions":[{"id":"https://openalex.org/I66855515","display_name":"Repsol (Spain)","ror":"https://ror.org/028bzjj61","country_code":"ES","type":"company","lineage":["https://openalex.org/I66855515"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Cristina Iba\u00f1ez-Llano","raw_affiliation_strings":["Repsol Technology Lab , Repsol , Spain"],"raw_orcid":"https://orcid.org/0009-0003-1917-3382","affiliations":[{"raw_affiliation_string":"Repsol Technology Lab , Repsol , Spain","institution_ids":["https://openalex.org/I66855515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051332139","display_name":"Sergio P\u00e9rez","orcid":"https://orcid.org/0000-0002-2191-4974"},"institutions":[{"id":"https://openalex.org/I66855515","display_name":"Repsol (Spain)","ror":"https://ror.org/028bzjj61","country_code":"ES","type":"company","lineage":["https://openalex.org/I66855515"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sergio P\u00e9rez","raw_affiliation_strings":["Repsol Technology Lab , Repsol , Spain"],"raw_orcid":"https://orcid.org/0000-0002-2191-4974","affiliations":[{"raw_affiliation_string":"Repsol Technology Lab , Repsol , Spain","institution_ids":["https://openalex.org/I66855515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004703726","display_name":"Fernando Fern\u00e1ndez","orcid":"https://orcid.org/0000-0003-3801-6801"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Fernando Fern\u00e1ndez","raw_affiliation_strings":["Computer Science Department , Universidad Carlos III de Madrid , Spain"],"raw_orcid":"https://orcid.org/0000-0003-3801-6801","affiliations":[{"raw_affiliation_string":"Computer Science Department , Universidad Carlos III de Madrid , Spain","institution_ids":["https://openalex.org/I50357001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004703726"],"corresponding_institution_ids":["https://openalex.org/I50357001"],"apc_list":null,"apc_paid":null,"fwci":0.339,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66541619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"13","issue":"4","first_page":"273","last_page":"287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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":0.9972000122070312,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9969000220298767,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9914000034332275,"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":0.8816079497337341},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7517891526222229},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.661169707775116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6372014284133911},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.6356267333030701},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.5500270128250122},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5392462611198425},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.475078284740448},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.45507633686065674},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15244150161743164},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09045219421386719}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8816079497337341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7517891526222229},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.661169707775116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6372014284133911},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.6356267333030701},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.5500270128250122},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5392462611198425},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.475078284740448},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.45507633686065674},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15244150161743164},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09045219421386719},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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:10.2478/jaiscr-2023-0019","is_oa":true,"landing_page_url":"https://doi.org/10.2478/jaiscr-2023-0019","pdf_url":"https://sciendo.com/pdf/10.2478/jaiscr-2023-0019","source":{"id":"https://openalex.org/S4210223945","display_name":"Journal of Artificial Intelligence and Soft Computing Research","issn_l":"2083-2567","issn":["2083-2567","2449-6499"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317241","host_organization_name":"Polish Neural Network Society, the University of Social Sciences in Lodz & Czestochowa University of Technology","host_organization_lineage":["https://openalex.org/P4310317241"],"host_organization_lineage_names":["Polish Neural Network Society, the University of Social Sciences in Lodz & Czestochowa University of Technology"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence and Soft Computing Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.2478/jaiscr-2023-0019","is_oa":true,"landing_page_url":"https://doi.org/10.2478/jaiscr-2023-0019","pdf_url":"https://sciendo.com/pdf/10.2478/jaiscr-2023-0019","source":{"id":"https://openalex.org/S4210223945","display_name":"Journal of Artificial Intelligence and Soft Computing Research","issn_l":"2083-2567","issn":["2083-2567","2449-6499"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317241","host_organization_name":"Polish Neural Network Society, the University of Social Sciences in Lodz & Czestochowa University of Technology","host_organization_lineage":["https://openalex.org/P4310317241"],"host_organization_lineage_names":["Polish Neural Network Society, the University of Social Sciences in Lodz & Czestochowa University of Technology"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence and Soft Computing Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8771039361","display_name":null,"funder_award_id":"PID2020-119367RB-I00","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320323770","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4388017139.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W1757796397","https://openalex.org/W2046376809","https://openalex.org/W2150593711","https://openalex.org/W2781726626","https://openalex.org/W2920362155","https://openalex.org/W2947150733","https://openalex.org/W3009584650","https://openalex.org/W3016525976","https://openalex.org/W3037024314","https://openalex.org/W3102100346","https://openalex.org/W3164731060","https://openalex.org/W4281392102","https://openalex.org/W4297792190","https://openalex.org/W4385372541","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W4386160446","https://openalex.org/W4387545330","https://openalex.org/W4387293922","https://openalex.org/W4226221094","https://openalex.org/W4226042081","https://openalex.org/W4221145086","https://openalex.org/W4284974072","https://openalex.org/W3207447243","https://openalex.org/W4293586040","https://openalex.org/W3133629861"],"abstract_inverted_index":{"Abstract":[0],"In":[1,28,65,99],"many":[2],"Reinforcement":[3],"Learning":[4],"(RL)":[5],"tasks,":[6],"the":[7,12,16,58,67,74,91,96,110,114,124,133,137,141,147,167],"classical":[8],"online":[9,156],"interaction":[10,23],"of":[11,47,53,119,166,186],"learning":[13,48,125,189],"agent":[14],"with":[15,109,154],"environment":[17,138],"is":[18,24,39,63,70,129,143],"impractical,":[19],"either":[20],"because":[21],"such":[22,172],"expensive":[25],"or":[26,116],"dangerous.":[27],"these":[29],"cases,":[30],"previous":[31],"gathered":[32],"data":[33,69,89],"can":[34,191],"be":[35],"used,":[36],"arising":[37],"what":[38],"typically":[40],"called":[41],"Offline":[42,169],"RL.":[43],"However,":[44],"this":[45,100],"type":[46],"faces":[49],"a":[50,80,84,104],"large":[51],"number":[52],"challenges,":[54],"mostly":[55],"derived":[56],"from":[57,87,136],"fact":[59],"that":[60,151,180],"exploration/exploitation":[61],"trade-off":[62],"overshadowed.":[64],"addition,":[66],"historical":[68,88],"usually":[71],"biased":[72],"by":[73,113],"way":[75],"it":[76,153],"was":[77],"obtained,":[78],"typically,":[79],"sub-optimal":[81],"controller,":[82],"producing":[83],"distributional":[85],"shift":[86],"and":[90,149,175],"one":[92],"required":[93],"to":[94,107,139],"learn":[95],"optimal":[97],"policy.":[98],"paper,":[101],"we":[102,178],"present":[103,146],"novel":[105],"approach":[106,128,148],"deal":[108],"uncertainty":[111],"risen":[112],"absence":[115],"sparse":[117],"presence":[118],"some":[120],"state-action":[121],"pairs":[122],"in":[123],"data.":[126],"Our":[127],"based":[130],"on":[131,184],"shaping":[132],"reward":[134],"perceived":[135],"ensure":[140],"task":[142],"solved.":[144],"We":[145],"show":[150,179],"combining":[152],"classic":[155],"RL":[157,170],"methods":[158],"make":[159],"them":[160],"perform":[161],"as":[162,164,173],"good":[163],"state":[165],"art":[168],"algorithms":[171,190],"CQL":[174],"BCQ.":[176],"Finally,":[177],"using":[181],"our":[182],"method":[183],"top":[185],"established":[187],"offline":[188],"improve":[192],"them.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-01T06:04:38.248271","created_date":"2025-10-10T00:00:00"}