{"id":"https://openalex.org/W4312616966","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892778","title":"Uncertainty Aware Model Integration on Reinforcement Learning","display_name":"Uncertainty Aware Model Integration on Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312616966","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892778"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892778","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":"2161-4407","issn":["2161-4407"],"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/A5062072698","display_name":"Takashi Nagata","orcid":"https://orcid.org/0000-0003-4569-1362"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takashi Nagata","raw_affiliation_strings":["University of California, Irvine,Computer Science,Irvine,USA","Computer Science, University of California, Irvine, Irvine, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Irvine,Computer Science,Irvine,USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Computer Science, University of California, Irvine, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049977157","display_name":"Jinwei Xing","orcid":"https://orcid.org/0000-0002-8085-2769"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]},{"id":"https://openalex.org/I4210140791","display_name":"Irvine University","ror":"https://ror.org/04ysmca02","country_code":"US","type":"education","lineage":["https://openalex.org/I4210140791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinwei Xing","raw_affiliation_strings":["University of California, Irvine,Cognitive Sciences,Irvine,USA","Cognitive Sciences, University of California, Irvine, Irvine, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Irvine,Cognitive Sciences,Irvine,USA","institution_ids":["https://openalex.org/I204250578","https://openalex.org/I4210140791"]},{"raw_affiliation_string":"Cognitive Sciences, University of California, Irvine, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006314011","display_name":"Tsutomu Kumazawa","orcid":"https://orcid.org/0000-0002-1096-1097"},"institutions":[{"id":"https://openalex.org/I4210130202","display_name":"Software Research Associates (Japan)","ror":"https://ror.org/02frcze54","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210130202"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsutomu Kumazawa","raw_affiliation_strings":["Software Research Associates, Inc.,Key Technology Laboratory,Tokyo,Japan","Key Technology Laboratory, Software Research Associates, Inc., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Research Associates, Inc.,Key Technology Laboratory,Tokyo,Japan","institution_ids":["https://openalex.org/I4210130202"]},{"raw_affiliation_string":"Key Technology Laboratory, Software Research Associates, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I4210130202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060924942","display_name":"Emre Neftci","orcid":"https://orcid.org/0000-0002-0332-3273"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]},{"id":"https://openalex.org/I4210140791","display_name":"Irvine University","ror":"https://ror.org/04ysmca02","country_code":"US","type":"education","lineage":["https://openalex.org/I4210140791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emre Neftci","raw_affiliation_strings":["University of California, Irvine,Cognitive Sciences,Irvine,USA","Cognitive Sciences, University of California, Irvine, Irvine, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Irvine,Cognitive Sciences,Irvine,USA","institution_ids":["https://openalex.org/I204250578","https://openalex.org/I4210140791"]},{"raw_affiliation_string":"Cognitive Sciences, University of California, Irvine, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs 1707 6347","issue":null,"first_page":"1","last_page":"7"},"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9901000261306763,"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":0.9549999833106995,"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":0.9037443399429321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.769874095916748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5816052556037903},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5514609813690186},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5494510531425476},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4638262987136841},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4548512101173401},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44463565945625305},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.41905975341796875}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9037443399429321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.769874095916748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5816052556037903},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5514609813690186},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5494510531425476},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4638262987136841},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4548512101173401},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44463565945625305},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.41905975341796875},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892778","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":"2161-4407","issn":["2161-4407"],"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":[],"awards":[{"id":"https://openalex.org/G7452611803","display_name":"CAREER: Scalable Neuromorphic Learning Machines","funder_award_id":"1652159","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W582134693","https://openalex.org/W1714211023","https://openalex.org/W1959608418","https://openalex.org/W1980035368","https://openalex.org/W2095705004","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2419990545","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2798494119","https://openalex.org/W2920362155","https://openalex.org/W2950471160","https://openalex.org/W2951266961","https://openalex.org/W2956805085","https://openalex.org/W2964043796","https://openalex.org/W2971130081","https://openalex.org/W2990747716","https://openalex.org/W2996314716","https://openalex.org/W3102961490","https://openalex.org/W3175557618","https://openalex.org/W4214717370","https://openalex.org/W4289294484","https://openalex.org/W4298206671","https://openalex.org/W6617145748","https://openalex.org/W6640963894","https://openalex.org/W6674330103","https://openalex.org/W6692846177","https://openalex.org/W6696324988","https://openalex.org/W6741002519","https://openalex.org/W6750253780","https://openalex.org/W6751494529","https://openalex.org/W6756256016","https://openalex.org/W6758854563","https://openalex.org/W6760405395","https://openalex.org/W6764214684","https://openalex.org/W6770858630","https://openalex.org/W6771936276","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3082178636","https://openalex.org/W2782041652","https://openalex.org/W2612657834","https://openalex.org/W2392157706","https://openalex.org/W2599192953","https://openalex.org/W2952088488","https://openalex.org/W1521968289","https://openalex.org/W4225691210","https://openalex.org/W4399568863","https://openalex.org/W2792147139"],"abstract_inverted_index":{"Model-based":[0],"reinforcement":[1,26],"learning":[2,27,30,118],"is":[3,19,58],"an":[4,34,55,92],"effective":[5],"approach":[6,154],"to":[7,48,88,98,107,115,145,156,166,178],"reducing":[8],"sample":[9],"complexity":[10],"by":[11,132],"adding":[12],"more":[13],"data":[14],"from":[15,31],"the":[16,40,43,51,65,81,96,109,112,116,122,133,140,146,164,180],"model.":[17,134,149],"Dyna":[18],"a":[20,37,59],"well-known":[21],"architecture":[22],"that":[23,121,152],"contains":[24],"model-based":[25],"and":[28,36,84],"integrates":[29],"interactions":[32],"with":[33],"environment":[35],"model":[38,44,57,77,97,113],"of":[39,64,69,80,111,182],"environment.":[41],"Although":[42],"can":[45],"greatly":[46],"help":[47],"speed":[49,162],"up":[50,163],"agent's":[52,82],"learning,":[53],"acquiring":[54],"accurate":[56],"hard":[60],"problem":[61],"in":[62],"spite":[63],"recent":[66],"great":[67],"success":[68],"function":[70],"approximation":[71],"using":[72],"neural":[73],"networks.":[74],"A":[75],"wrong":[76],"causes":[78],"degradation":[79],"performance":[83],"raises":[85],"another":[86],"question:":[87],"which":[89],"extent":[90],"should":[91],"agent":[93,123,165],"rely":[94],"on":[95,129,173],"update":[99],"its":[100,126],"policy?":[101],"In":[102],"this":[103,153],"paper,":[104],"we":[105,138],"propose":[106],"use":[108],"confidence":[110],"simulations":[114,131],"integrated":[117],"process":[119],"so":[120],"avoids":[124],"updating":[125],"policy":[127],"based":[128],"uncertain":[130],"To":[135],"obtain":[136],"confidence,":[137],"apply":[139],"Monte":[141],"Carlo":[142],"dropout":[143],"technique":[144],"state":[147],"transition":[148],"We":[150,170],"show":[151],"contributes":[155],"improving":[157],"early-stage":[158],"training,":[159],"thus":[160],"helping":[161],"reach":[167],"reasonable":[168],"performance.":[169],"conduct":[171],"experiments":[172],"simulated":[174],"robotic":[175],"locomotion":[176],"tasks":[177],"demonstrate":[179],"effectiveness":[181],"our":[183],"approach.":[184]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}