{"id":"https://openalex.org/W2978242174","doi":"https://doi.org/10.1109/ijcnn.2019.8852234","title":"Efficient and Scalable Exploration via Estimation-Error","display_name":"Efficient and Scalable Exploration via Estimation-Error","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2978242174","doi":"https://doi.org/10.1109/ijcnn.2019.8852234","mag":"2978242174"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5002670314","display_name":"Chuxiong Sun","orcid":"https://orcid.org/0000-0002-4956-6924"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuxiong Sun","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431222","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0002-2974-0972"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077376806","display_name":"Ruiying Li","orcid":"https://orcid.org/0000-0001-8044-4813"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiying Li","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050490442","display_name":"Jiao Wu","orcid":"https://orcid.org/0000-0003-1716-9235"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiao Wu","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100740224","display_name":"Xiaohui Hu","orcid":"https://orcid.org/0000-0001-5717-8676"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Hu","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":null,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9923999905586243,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9896000027656555,"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/computer-science","display_name":"Computer science","score":0.7882579565048218},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7881795167922974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6413151025772095},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5732307434082031},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5703717470169067},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5520751476287842},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5357270836830139},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5226190686225891},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4561260938644409},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.448927104473114},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4188210964202881},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41849544644355774},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11463102698326111}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7882579565048218},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7881795167922974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6413151025772095},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5732307434082031},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5703717470169067},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5520751476287842},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5357270836830139},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5226190686225891},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4561260938644409},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.448927104473114},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4188210964202881},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41849544644355774},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11463102698326111},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8852234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W779494576","https://openalex.org/W1542595278","https://openalex.org/W1771410628","https://openalex.org/W1988526405","https://openalex.org/W2000514530","https://openalex.org/W2034806191","https://openalex.org/W2121863487","https://openalex.org/W2123327324","https://openalex.org/W2124352385","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2280163991","https://openalex.org/W2417786368","https://openalex.org/W2556958149","https://openalex.org/W2561776174","https://openalex.org/W2593766708","https://openalex.org/W2596982695","https://openalex.org/W2604960773","https://openalex.org/W2623491082","https://openalex.org/W2663108269","https://openalex.org/W2724169821","https://openalex.org/W2727115052","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2749928749","https://openalex.org/W2751973545","https://openalex.org/W2885550588","https://openalex.org/W2949475445","https://openalex.org/W2951799221","https://openalex.org/W2962767126","https://openalex.org/W2963095800","https://openalex.org/W2963160877","https://openalex.org/W2963276097","https://openalex.org/W2963359646","https://openalex.org/W2963523627","https://openalex.org/W2963639957","https://openalex.org/W2963712109","https://openalex.org/W2963864421","https://openalex.org/W2963938771","https://openalex.org/W2964043796","https://openalex.org/W2964064620","https://openalex.org/W2964174623","https://openalex.org/W2974778612","https://openalex.org/W3103780890","https://openalex.org/W4297791094","https://openalex.org/W4297804636","https://openalex.org/W6622487243","https://openalex.org/W6632504492","https://openalex.org/W6638018090","https://openalex.org/W6650587873","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6695011786","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6730111887","https://openalex.org/W6730641667","https://openalex.org/W6734097942","https://openalex.org/W6735033012","https://openalex.org/W6735939104","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6740229589","https://openalex.org/W6741002519","https://openalex.org/W6743802245","https://openalex.org/W6748271565","https://openalex.org/W6753925943"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Exploring":[0],"efficiently":[1],"in":[2,10,19,30,46,174,197],"complex":[3,134,198],"environments":[4,135,178,199],"is":[5],"still":[6,70],"a":[7,107,114],"challenging":[8,154],"problem":[9],"reinforcement":[11,61],"learning.":[12],"Recent":[13],"exploration":[14,78,188],"algorithms":[15,69],"based":[16],"on":[17,38,152],"\"optimism":[18],"the":[20,56,65,72,85,94,104,144,153,204],"face":[21],"of":[22,58,146],"uncertainty\"":[23],"or":[24,165],"intrinsic":[25],"motivation":[26],"achieved":[27],"promising":[28],"performance":[29,168],"sparse":[31],"reward":[32,115,119],"settings,":[33],"but":[34],"they":[35],"often":[36],"rely":[37],"additional":[39],"structures":[40],"which":[41,130],"are":[42,181],"hard":[43],"to":[44,92,118,133,142,170,193],"build":[45],"large":[47],"scale":[48,132],"problems.":[49],"It":[50],"renders":[51],"them":[52],"impractical":[53],"and":[54,98,110,200],"hinders":[55],"process":[57],"combining":[59],"with":[60,136],"learning":[62],"algorithms.":[63],"Hence,":[64],"most":[66],"state-of-the-art":[67],"RL":[68],"use":[71],"naive":[73,205],"action":[74,99,171,206],"space":[75,172,207],"noise":[76,173],"as":[77,113],"strategy.":[79],"In":[80,122,140],"this":[81,123],"paper,":[82],"we":[83,102,125,149],"model":[84],"uncertainty":[86,105],"about":[87],"environment":[88],"through":[89],"agent's":[90],"ability":[91],"estimate":[93],"value":[95],"across":[96],"state":[97],"space.":[100],"Then,":[101],"parameterize":[103],"by":[106],"neural":[108],"network":[109],"regard":[111],"it":[112,151,201],"bonus":[116,129],"signal":[117],"uncertain":[120],"states.":[121],"way,":[124],"generate":[126],"an":[127],"end-to-end":[128],"can":[131,190],"less":[137],"computational":[138],"cost.":[139],"order":[141],"prove":[143],"effectiveness":[145],"our":[147,161,187],"method,":[148],"evaluate":[150],"Atari":[155],"2600":[156],"games.":[157],"We":[158],"observed":[159],"that":[160,186],"method":[162,189],"achieves":[163],"superior":[164],"comparable":[166],"exploratory":[167],"compared":[169],"all":[175],"environments,":[176],"including":[177],"whose":[179],"rewards":[180],"sparse.":[182],"The":[183],"results":[184],"demonstrate":[185],"motivate":[191],"agent":[192],"explore":[194],"effectively":[195],"even":[196],"generally":[202],"outperforms":[203],"noise.":[208]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}