{"id":"https://openalex.org/W3129659662","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892633","title":"Q-Value Weighted Regression: Reinforcement Learning with Limited Data","display_name":"Q-Value Weighted Regression: Reinforcement Learning with Limited Data","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W3129659662","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892633","mag":"3129659662"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892633","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5031843495","display_name":"Piotr Kozakowski","orcid":null},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]},{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Piotr Kozakowski","raw_affiliation_strings":["Faculty of Mathematics, Informatics and Mechanics University of Warsaw,Warsaw,Poland","Faculty of Mathematics, Informatics and Mechanics University of Warsaw, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics, Informatics and Mechanics University of Warsaw,Warsaw,Poland","institution_ids":["https://openalex.org/I108403487","https://openalex.org/I4654613"]},{"raw_affiliation_string":"Faculty of Mathematics, Informatics and Mechanics University of Warsaw, Warsaw, Poland","institution_ids":["https://openalex.org/I4654613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031789995","display_name":"\u0141ukasz Kaiser","orcid":"https://orcid.org/0000-0003-1092-6010"},"institutions":[{"id":"https://openalex.org/I4210161460","display_name":"OpenAI (United States)","ror":"https://ror.org/05wx9n238","country_code":"US","type":"company","lineage":["https://openalex.org/I4210161460"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lukasz Kaiser","raw_affiliation_strings":["OpenAI,San Francisco,United States","OpenAI, San Francisco, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OpenAI,San Francisco,United States","institution_ids":["https://openalex.org/I4210161460"]},{"raw_affiliation_string":"OpenAI, San Francisco, United States","institution_ids":["https://openalex.org/I4210161460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016302450","display_name":"Henryk Michalewski","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henryk Michalewski","raw_affiliation_strings":["Google,Warsaw,Poland","Google, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Warsaw,Poland","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Warsaw, Poland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081121649","display_name":"Afroz Mohiuddin","orcid":"https://orcid.org/0000-0002-6310-7660"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Afroz Mohiuddin","raw_affiliation_strings":["Google,Mountain View,United States","Google, Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Mountain View,United States","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059209372","display_name":"Katarzyna Ka\u0144ska","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katarzyna Kanska","raw_affiliation_strings":["Google,Warsaw,Poland","Google, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Warsaw,Poland","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Warsaw, Poland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"70","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":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9936000108718872,"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":0.989799976348877,"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/hyperparameter","display_name":"Hyperparameter","score":0.8511796593666077},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7879834175109863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6655867695808411},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6636263132095337},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.6419140100479126},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6031997799873352},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5261679887771606},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5239073038101196},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4506445825099945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4331132769584656},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4163965880870819},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25767695903778076},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22449731826782227},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1306193768978119},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08494088053703308}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8511796593666077},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7879834175109863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6655867695808411},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6636263132095337},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.6419140100479126},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6031997799873352},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5261679887771606},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5239073038101196},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4506445825099945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4331132769584656},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4163965880870819},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25767695903778076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22449731826782227},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1306193768978119},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08494088053703308},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892633","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1673923490","https://openalex.org/W1757796397","https://openalex.org/W2109169869","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2126685977","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2173248099","https://openalex.org/W2534269850","https://openalex.org/W2573393487","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2749807327","https://openalex.org/W2761873684","https://openalex.org/W2772709170","https://openalex.org/W2781726626","https://openalex.org/W2799151646","https://openalex.org/W2892110489","https://openalex.org/W2902907165","https://openalex.org/W2904453761","https://openalex.org/W2920362155","https://openalex.org/W2950220847","https://openalex.org/W2952629144","https://openalex.org/W2952867909","https://openalex.org/W2958416396","https://openalex.org/W2962957005","https://openalex.org/W2963423916","https://openalex.org/W2963664410","https://openalex.org/W2963674921","https://openalex.org/W2963864421","https://openalex.org/W2963884015","https://openalex.org/W2964043796","https://openalex.org/W2964153729","https://openalex.org/W2978455699","https://openalex.org/W2990747716","https://openalex.org/W2995706821","https://openalex.org/W3022566517","https://openalex.org/W3034607397","https://openalex.org/W3034786558","https://openalex.org/W3037440645","https://openalex.org/W3041890730","https://openalex.org/W3137695714","https://openalex.org/W3169514089","https://openalex.org/W4214717370","https://openalex.org/W4287724327","https://openalex.org/W4287756699","https://openalex.org/W4298876402","https://openalex.org/W6637162671","https://openalex.org/W6678925830","https://openalex.org/W6683204974","https://openalex.org/W6683300800","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6728925229","https://openalex.org/W6739659843","https://openalex.org/W6747473740","https://openalex.org/W6780159193","https://openalex.org/W6780470247"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4318719684","https://openalex.org/W4389724018","https://openalex.org/W4318559728","https://openalex.org/W3183136280","https://openalex.org/W2775233965","https://openalex.org/W3114716045","https://openalex.org/W4281847915"],"abstract_inverted_index":{"Sample":[0],"efficiency":[1,50],"has":[2,47],"emerged":[3],"as":[4],"a":[5,18,120,127,138],"significant":[6],"challenge":[7],"of":[8,64,116,124,129],"deep":[9],"reinforcement":[10],"learning.":[11],"We":[12,57,77],"introduce":[13],"Q-Value":[14],"Weighted":[15,31],"Regression":[16,32],"(QWR),":[17],"simple":[19],"RL":[20],"algorithm":[21,37,141],"that":[22,38,66,80],"excels":[23],"in":[24],"this":[25],"aspect.":[26],"QWR":[27,81,99,136],"builds":[28],"upon":[29],"Advantage":[30],"(AWR),":[33],"an":[34],"off-policy":[35],"actor-critic":[36],"performs":[39],"very":[40],"well":[41],"on":[42,90,102,106,126],"continuous":[43,93],"control":[44],"tasks,":[45],"but":[46],"low":[48],"sample":[49],"and":[51,61,70,94,110,145],"struggles":[52],"with":[53,92,104,112],"high-dimensional":[54],"observation":[55],"spaces.":[56],"perform":[58],"both":[59,89,143],"theoretical":[60],"empirical":[62],"analyses":[63],"AWR,":[65],"explain":[67],"its":[68],"shortcomings":[69],"use":[71],"these":[72],"insights":[73],"to":[74],"motivate":[75],"QWR.":[76],"show":[78],"experimentally":[79],"either":[82],"outperforms":[83,119],"or":[84],"matches":[85],"the":[86,107,113,133],"state-of-the-art":[87],"algorithms":[88],"tasks":[91],"discrete":[95],"actions.":[96],"In":[97],"particular,":[98],"yields":[100],"results":[101],"par":[103],"SAC":[105,144],"MuJoCo":[108],"suite":[109],"-":[111,118],"same":[114,134],"set":[115,128],"hyperparameters":[117],"highly":[121],"tuned":[122],"implementation":[123],"Rainbow":[125],"Atari":[130],"games.":[131],"At":[132],"time,":[135],"is":[137],"much":[139],"simpler":[140],"than":[142],"Rainbow.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}