{"id":"https://openalex.org/W2910568379","doi":"https://doi.org/10.1109/tnnls.2021.3089425","title":"The Wisdom of the Crowd: Reliable Deep Reinforcement Learning Through Ensembles of Q-Functions","display_name":"The Wisdom of the Crowd: Reliable Deep Reinforcement Learning Through Ensembles of Q-Functions","publication_year":2021,"publication_date":"2021-06-29","ids":{"openalex":"https://openalex.org/W2910568379","doi":"https://doi.org/10.1109/tnnls.2021.3089425","mag":"2910568379","pmid":"https://pubmed.ncbi.nlm.nih.gov/34185651"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3089425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3089425","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mountainscholar.org/bitstreams/e27fe503-0048-4fa9-8530-2917fb44455c/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086517426","display_name":"Daniel L. Elliott","orcid":"https://orcid.org/0000-0001-9125-592X"},"institutions":[{"id":"https://openalex.org/I4210141911","display_name":"Lindsay Unified School District","ror":"https://ror.org/03sje1a87","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141911"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel L. Elliott","raw_affiliation_strings":["Lindsay Corporation, Omaha, NE, USA"],"raw_orcid":"https://orcid.org/0000-0001-9125-592X","affiliations":[{"raw_affiliation_string":"Lindsay Corporation, Omaha, NE, USA","institution_ids":["https://openalex.org/I4210141911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036335957","display_name":"Charles W. Anderson","orcid":"https://orcid.org/0000-0001-7392-3840"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Anderson","raw_affiliation_strings":["Department of Computer Science, Colorado State University, Fort Collins, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Colorado State University, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I92446798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086517426"],"corresponding_institution_ids":["https://openalex.org/I4210141911"],"apc_list":null,"apc_paid":null,"fwci":1.8198,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87386121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"34","issue":"1","first_page":"43","last_page":"51"},"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/T10581","display_name":"Neural dynamics and brain function","score":0.95169997215271,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.940500020980835,"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":0.8650861382484436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7358921766281128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7330477833747864},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6586583256721497},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6307015419006348},{"id":"https://openalex.org/keywords/crowds","display_name":"Crowds","score":0.625807523727417},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5237036943435669},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4810250401496887},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.42224985361099243},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.418089359998703},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18898144364356995}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8650861382484436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7358921766281128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7330477833747864},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6586583256721497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6307015419006348},{"id":"https://openalex.org/C2777852691","wikidata":"https://www.wikidata.org/wiki/Q13430821","display_name":"Crowds","level":2,"score":0.625807523727417},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5237036943435669},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4810250401496887},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.42224985361099243},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.418089359998703},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18898144364356995},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2021.3089425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3089425","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34185651","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34185651","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:mountainscholar.org:10217/191477","is_oa":true,"landing_page_url":"https://hdl.handle.net/10217/191477","pdf_url":"https://mountainscholar.org/bitstreams/e27fe503-0048-4fa9-8530-2917fb44455c/download","source":{"id":"https://openalex.org/S4306402292","display_name":"Digital Collections of Colorado (Colorado State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I92446798","host_organization_name":"Colorado State University","host_organization_lineage":["https://openalex.org/I92446798"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:mountainscholar.org:10217/191477","is_oa":true,"landing_page_url":"https://hdl.handle.net/10217/191477","pdf_url":"https://mountainscholar.org/bitstreams/e27fe503-0048-4fa9-8530-2917fb44455c/download","source":{"id":"https://openalex.org/S4306402292","display_name":"Digital Collections of Colorado (Colorado State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I92446798","host_organization_name":"Colorado State University","host_organization_lineage":["https://openalex.org/I92446798"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2910568379.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1623881903","https://openalex.org/W1750311484","https://openalex.org/W1988790447","https://openalex.org/W2043806097","https://openalex.org/W2051812123","https://openalex.org/W2064556564","https://openalex.org/W2101881799","https://openalex.org/W2103311328","https://openalex.org/W2135293965","https://openalex.org/W2145339207","https://openalex.org/W2145534813","https://openalex.org/W2150884987","https://openalex.org/W2161230965","https://openalex.org/W2168342951","https://openalex.org/W2257979135","https://openalex.org/W2402590133","https://openalex.org/W2549225575","https://openalex.org/W2746553466","https://openalex.org/W2795729123","https://openalex.org/W2910568379","https://openalex.org/W3004732066","https://openalex.org/W4212883601","https://openalex.org/W4214717370","https://openalex.org/W4249247059","https://openalex.org/W6631190155","https://openalex.org/W6636881020","https://openalex.org/W6637617981","https://openalex.org/W6675217247","https://openalex.org/W6677067356","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6692846177"],"related_works":["https://openalex.org/W4240200267","https://openalex.org/W1511510665","https://openalex.org/W1524661185","https://openalex.org/W2078823605","https://openalex.org/W2500095415","https://openalex.org/W4233026749","https://openalex.org/W2097922264","https://openalex.org/W2282342021","https://openalex.org/W4248106174","https://openalex.org/W627242580"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,87,164],"(RL)":[2],"agents":[3],"learn":[4],"by":[5,62,73],"exploring":[6],"the":[7,18,25,53,69,85,101,118,139,146,150,154,161,185],"environment":[8],"and":[9,45,125],"then":[10],"exploiting":[11],"what":[12],"they":[13],"have":[14,94],"learned.":[15],"This":[16],"frees":[17],"human":[19],"trainers":[20],"from":[21],"having":[22],"to":[23,84,169,183,190],"know":[24],"preferred":[26],"action":[27,151],"or":[28],"intrinsic":[29],"value":[30],"of":[31,37,71,132,145,149,153,187],"each":[32],"encountered":[33],"state.":[34],"The":[35,129],"cost":[36],"this":[38,133,178],"freedom":[39],"is":[40,43,135,141],"that":[41,55,117,138,160,177],"RL":[42,102,126],"slower":[44],"more":[46,171],"unstable":[47],"than":[48],"supervised":[49,86],"learning.":[50],"We":[51],"explore":[52],"possibility":[54],"ensemble":[56],"methods":[57],"can":[58,180],"remedy":[59],"these":[60],"shortcomings":[61],"investigating":[63],"a":[64,79,106,136,142,195],"novel":[65],"technique":[66],"which":[67,193],"harnesses":[68],"wisdom":[70],"crowds":[72],"combining":[74],"Q-function":[75],"approximator":[76],"estimates":[77],"utilizing":[78],"simple":[80],"combination":[81],"scheme":[82],"similar":[83],"approach":[88,120,179],"known":[89],"as":[90],"bagging.":[91],"Bagging":[92],"approaches":[93,127],"not":[95],"yet":[96],"found":[97],"widespread":[98],"adoption":[99],"in":[100,163],"literature":[103],"nor":[104],"has":[105],"comprehensive":[107],"look":[108],"at":[109],"its":[110],"performance":[111],"been":[112],"performed.":[113],"Our":[114],"results":[115],"show":[116,176],"proposed":[119],"improves":[121],"all":[122],"three":[123],"tasks":[124],"attempted.":[128],"primary":[130],"contribution":[131],"work":[134],"demonstration":[137],"improvement":[140],"direct":[143],"result":[144],"increased":[147],"stability":[148,162],"portion":[152],"state-action-value":[155],"function.":[156],"Subsequent":[157],"experimentation":[158],"demonstrates":[159],"allows":[165],"an":[166],"actor-critic":[167],"method":[168],"find":[170],"efficient":[172],"solutions.":[173],"Finally":[174],"we":[175],"be":[181],"used":[182],"decrease":[184],"amount":[186],"time":[188],"necessary":[189],"solve":[191],"problems":[192],"require":[194],"deep":[196],"Q-learning":[197],"(DQN)":[198],"approach.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}