{"id":"https://openalex.org/W3045981309","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206677","title":"The Deep Quality-Value Family of Deep Reinforcement Learning Algorithms","display_name":"The Deep Quality-Value Family of Deep Reinforcement Learning Algorithms","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3045981309","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206677","mag":"3045981309"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbi.uliege.be/handle/2268/249809","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074266137","display_name":"Matthia Sabatelli","orcid":"https://orcid.org/0009-0007-7540-8616"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Matthia Sabatelli","raw_affiliation_strings":["Montefiore Institute, Li\u00e8ge, Belgium"],"affiliations":[{"raw_affiliation_string":"Montefiore Institute, Li\u00e8ge, Belgium","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017670779","display_name":"Gilles Louppe","orcid":"https://orcid.org/0000-0002-2082-3106"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gilles Louppe","raw_affiliation_strings":["Montefiore Institute, Li\u00e8ge, Belgium"],"affiliations":[{"raw_affiliation_string":"Montefiore Institute, Li\u00e8ge, Belgium","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002322091","display_name":"Pierre Geurts","orcid":"https://orcid.org/0000-0001-8527-5000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre Geurts","raw_affiliation_strings":["Montefiore Institute, Li\u00e8ge, Belgium"],"affiliations":[{"raw_affiliation_string":"Montefiore Institute, Li\u00e8ge, Belgium","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060596453","display_name":"Marco Wiering","orcid":"https://orcid.org/0000-0003-4331-7537"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marco A. Wiering","raw_affiliation_strings":["University of Groningen, Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Groningen, Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074266137"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4059,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6959927,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"8","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":0.9995999932289124,"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":0.9995999932289124,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9739999771118164,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.97079998254776,"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":0.8770031929016113},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.7449303865432739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6900108456611633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6130865812301636},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5877436995506287},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5490359663963318},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5411007404327393},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5273020267486572},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4830396771430969},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46851229667663574},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4676738679409027},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.4519283175468445},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42988860607147217},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.26208311319351196},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20987674593925476}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8770031929016113},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.7449303865432739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6900108456611633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6130865812301636},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5877436995506287},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5490359663963318},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5411007404327393},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5273020267486572},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4830396771430969},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46851229667663574},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4676738679409027},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.4519283175468445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42988860607147217},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26208311319351196},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20987674593925476},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:orbi.ulg.ac.be:2268/249809","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/249809","pdf_url":null,"source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Joint Conference on Neural Networks (IJCNN 2020) (2020-07)","raw_type":"peer reviewed"}],"best_oa_location":{"id":"pmh:oai:orbi.ulg.ac.be:2268/249809","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/249809","pdf_url":null,"source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Joint Conference on Neural Networks (IJCNN 2020) (2020-07)","raw_type":"peer reviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1546167776","https://openalex.org/W2100677568","https://openalex.org/W2115211925","https://openalex.org/W2121863487","https://openalex.org/W2134140787","https://openalex.org/W2137766593","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2580175322","https://openalex.org/W2588283865","https://openalex.org/W2724169821","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2902098903","https://openalex.org/W2919115771","https://openalex.org/W2924131335","https://openalex.org/W2951799221","https://openalex.org/W2964174623","https://openalex.org/W2964291307","https://openalex.org/W3041202696","https://openalex.org/W3103559770","https://openalex.org/W3103780890","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W6680313055","https://openalex.org/W6685444567","https://openalex.org/W6732665253","https://openalex.org/W6740092555","https://openalex.org/W6760724441"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W2742483371","https://openalex.org/W3038962357","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3099153698","https://openalex.org/W2025663273","https://openalex.org/W4399155503"],"abstract_inverted_index":{"We":[0,22,38,73],"present":[1,109],"a":[2],"novel":[3],"approach":[4],"for":[5,63],"learning":[6,30,53,65],"an":[7,31,92],"approximation":[8,27,32,93],"of":[9,33,77,94,140],"the":[10,34,66,70,75,95,137,141],"optimal":[11],"state-action":[12],"value":[13],"function":[14,36,68],"(Q)":[15],"in":[16],"model-free":[17],"Deep":[18],"Reinforcement":[19],"Learning":[20],"(DRL).":[21],"propose":[23],"to":[24,86,130],"learn":[25,91],"this":[26,51,78],"while":[28],"simultaneously":[29],"state-value":[35],"(V).":[37],"introduce":[39],"two":[40,60],"new":[41],"DRL":[42,87,122],"algorithms,":[43],"called":[44],"DQV-Learning":[45],"and":[46,69,100,107,127,133],"DQV-Max":[47,108],"Learning,":[48],"which":[49,89,125],"follow":[50],"specific":[52],"dynamic.":[54],"In":[55],"short,":[56],"both":[57],"algorithms":[58,85],"use":[59],"neural":[61],"networks":[62],"separately":[64],"V":[67],"Q":[71,96,142],"function.":[72,143],"validate":[74],"effectiveness":[76],"training":[79],"scheme":[80],"by":[81],"thoroughly":[82],"comparing":[83],"our":[84],"methods":[88],"only":[90],"function,":[97],"namely":[98],"DQN":[99,126],"DDQN.":[101],"Our":[102],"results":[103],"show":[104],"that":[105],"DQV":[106],"several":[110],"important":[111],"benefits:":[112],"they":[113],"converge":[114],"significantly":[115],"faster,":[116],"can":[117],"achieve":[118],"super-human":[119],"performance":[120],"on":[121,124],"testbeds":[123],"DDQN":[128],"failed":[129],"do":[131],"so,":[132],"suffer":[134],"less":[135],"from":[136],"overestimation":[138],"bias":[139]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}