{"id":"https://openalex.org/W4285193323","doi":"https://doi.org/10.1109/tg.2022.3185330","title":"Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise","display_name":"Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise","publication_year":2022,"publication_date":"2022-06-22","ids":{"openalex":"https://openalex.org/W4285193323","doi":"https://doi.org/10.1109/tg.2022.3185330"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2022.3185330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2022.3185330","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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 Games","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.01004","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048689963","display_name":"Li Meng","orcid":"https://orcid.org/0000-0002-8867-9104"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Li Meng","raw_affiliation_strings":["University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-8867-9104","affiliations":[{"raw_affiliation_string":"University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002394922","display_name":"Morten Goodwin","orcid":"https://orcid.org/0000-0001-6331-702X"},"institutions":[{"id":"https://openalex.org/I184531372","display_name":"OsloMet \u2013 Oslo Metropolitan University","ror":"https://ror.org/04q12yn84","country_code":"NO","type":"education","lineage":["https://openalex.org/I184531372"]},{"id":"https://openalex.org/I200650556","display_name":"University of Agder","ror":"https://ror.org/03x297z98","country_code":"NO","type":"education","lineage":["https://openalex.org/I200650556"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Morten Goodwin","raw_affiliation_strings":["Centre for Artificial Intelligence Research, University of Agder, Kristiansand, Norway","Oslo Metropolitan University, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence Research, University of Agder, Kristiansand, Norway","institution_ids":["https://openalex.org/I200650556"]},{"raw_affiliation_string":"Oslo Metropolitan University, Oslo, Norway","institution_ids":["https://openalex.org/I184531372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032770006","display_name":"Anis Yazidi","orcid":"https://orcid.org/0000-0001-7591-1659"},"institutions":[{"id":"https://openalex.org/I1281400175","display_name":"Oslo University Hospital","ror":"https://ror.org/00j9c2840","country_code":"NO","type":"healthcare","lineage":["https://openalex.org/I1281400175"]},{"id":"https://openalex.org/I184531372","display_name":"OsloMet \u2013 Oslo Metropolitan University","ror":"https://ror.org/04q12yn84","country_code":"NO","type":"education","lineage":["https://openalex.org/I184531372"]},{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Anis Yazidi","raw_affiliation_strings":["Oslo Metropolitan University, Oslo, Norway","Norwegian University of Science and Technology, Trondheim, Norway","Oslo University Hospital, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0001-7591-1659","affiliations":[{"raw_affiliation_string":"Oslo Metropolitan University, Oslo, Norway","institution_ids":["https://openalex.org/I184531372"]},{"raw_affiliation_string":"Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Oslo University Hospital, Oslo, Norway","institution_ids":["https://openalex.org/I1281400175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090446312","display_name":"Paal Engelstad","orcid":"https://orcid.org/0009-0000-8371-927X"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Paal E. Engelstad","raw_affiliation_strings":["University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3486,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64342476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"15","issue":"4","first_page":"580","last_page":"589"},"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":0.9955000281333923,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6388905048370361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6070340871810913},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5551900863647461},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.509945273399353},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.47517508268356323},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4633311331272125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44878271222114563},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.08594313263893127}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6388905048370361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6070340871810913},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5551900863647461},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.509945273399353},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.47517508268356323},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4633311331272125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44878271222114563},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.08594313263893127},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/tg.2022.3185330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2022.3185330","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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 Games","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2203.01004","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.01004","pdf_url":"https://arxiv.org/pdf/2203.01004","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ntnuopen.ntnu.no:11250/3057551","is_oa":true,"landing_page_url":"https://hdl.handle.net/11250/3057551","pdf_url":null,"source":{"id":"https://openalex.org/S4306401716","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"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":"10","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:oda.oslomet.no:11250/3047297","is_oa":true,"landing_page_url":"https://hdl.handle.net/11250/3047297","pdf_url":null,"source":{"id":"https://openalex.org/S4306401716","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"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":"IEEE Transactions on Games (TG)","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:uia.brage.unit.no:11250/3052785","is_oa":true,"landing_page_url":"https://hdl.handle.net/11250/3052785","pdf_url":null,"source":{"id":"https://openalex.org/S4306401716","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"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":"1-10","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:www.duo.uio.no:10852/99676","is_oa":true,"landing_page_url":"http://hdl.handle.net/10852/99676","pdf_url":null,"source":{"id":"https://openalex.org/S4306401716","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"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":"2475-1502","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.01004","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.01004","pdf_url":"https://arxiv.org/pdf/2203.01004","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1731361040","display_name":null,"funder_award_id":"#270053","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"}],"funders":[{"id":"https://openalex.org/F4320323260","display_name":"Universitetet i Oslo","ror":"https://ror.org/01xtthb56"},{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W51508254","https://openalex.org/W1542595278","https://openalex.org/W1557517019","https://openalex.org/W1579979603","https://openalex.org/W2101493843","https://openalex.org/W2115804631","https://openalex.org/W2121517924","https://openalex.org/W2145339207","https://openalex.org/W2280163991","https://openalex.org/W2559655401","https://openalex.org/W2596585349","https://openalex.org/W2623491082","https://openalex.org/W2724169821","https://openalex.org/W2746553466","https://openalex.org/W2788862220","https://openalex.org/W2807588596","https://openalex.org/W2914261249","https://openalex.org/W2951799221","https://openalex.org/W2954540134","https://openalex.org/W2963277051","https://openalex.org/W2963403143","https://openalex.org/W2963438456","https://openalex.org/W2974778612","https://openalex.org/W3018036994","https://openalex.org/W3020125231","https://openalex.org/W3128125614","https://openalex.org/W3129322645","https://openalex.org/W3169291081","https://openalex.org/W4206547457","https://openalex.org/W4234228486","https://openalex.org/W4287018575","https://openalex.org/W4287779179","https://openalex.org/W4293405734","https://openalex.org/W4294397380","https://openalex.org/W4298857966","https://openalex.org/W6602057636","https://openalex.org/W6631190155","https://openalex.org/W6632504492","https://openalex.org/W6634861202","https://openalex.org/W6637967152","https://openalex.org/W6639039794","https://openalex.org/W6677067356","https://openalex.org/W6677314451","https://openalex.org/W6683608605","https://openalex.org/W6685444567","https://openalex.org/W6695011786","https://openalex.org/W6718092244","https://openalex.org/W6735939104","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6748603076","https://openalex.org/W6752244597","https://openalex.org/W6752301220","https://openalex.org/W6758978475","https://openalex.org/W6765696844","https://openalex.org/W6778000925","https://openalex.org/W6796289742","https://openalex.org/W6800570120"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W3122088529","https://openalex.org/W2378211422","https://openalex.org/W3041320102","https://openalex.org/W2111669074","https://openalex.org/W2085259108","https://openalex.org/W3123087812"],"abstract_inverted_index":{"Q-learning":[0],"is":[1,25,74],"one":[2],"of":[3,46,61,70,80,101,112,158,171,191],"the":[4,44,59,62,68,78,83,86,99,102,110,119,137,146,159,189],"most":[5],"well-known":[6],"reinforcement":[7],"learning":[8],"algorithms.":[9,151],"There":[10],"have":[11],"been":[12],"tremendous":[13],"efforts":[14],"to":[15,34,58,125,144],"develop":[16],"this":[17,105,130],"algorithm":[18,143,162],"using":[19],"neural":[20,31],"networks.":[21],"Bootstrapped":[22],"deepQ-learning":[23,72,161],"network":[24,32,73],"amongst":[26],"them.":[27],"It":[28],"utilizes":[29],"multiple":[30],"heads":[33],"introduce":[35,126],"diversity":[36,81,128],"intoQ-learning.":[37],"Diversity":[38],"can":[39,51,182],"sometimes":[40],"be":[41],"viewed":[42],"as":[43],"amount":[45],"reasonable":[47],"moves":[48],"an":[49],"agent":[50],"take":[52],"at":[53],"a":[54,94,122],"given":[55],"state,":[56],"analogous":[57],"definition":[60],"exploration":[63],"ratio":[64],"in":[65],"RL.":[66],"Thus,":[67,174],"performance":[69,100,186],"bootstrapped":[71,160,184],"deeply":[75],"connected":[76],"with":[77,115,180],"level":[79],"within":[82],"algorithm.":[84,131],"In":[85,104],"original":[87,147],"research,":[88],"it":[89],"was":[90],"pointed":[91],"out":[92],"that":[93,155,177],"random":[95],"prior":[96],"could":[97],"improve":[98,183],"model.":[103],"article,":[106],"we":[107,175],"further":[108],"explore":[109],"possibility":[111],"replacing":[113,178],"priors":[114,179],"noise":[116,120,181],"and":[117,140,148],"sample":[118],"from":[121],"Gaussian":[123],"distribution":[124],"more":[127],"into":[129],"We":[132],"conduct":[133],"our":[134,142,156],"experiment":[135],"on":[136],"Atari":[138,172],"benchmark":[139],"compare":[141],"both":[145],"other":[149],"related":[150],"The":[152],"results":[153],"show":[154],"modification":[157],"achieves":[163],"significantly":[164],"higher":[165],"evaluation":[166],"scores":[167],"across":[168],"different":[169],"types":[170],"games.":[173],"conclude":[176],"deepQ-learning's":[185],"by":[187],"ensuring":[188],"integrity":[190],"diversities.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}