{"id":"https://openalex.org/W4312564987","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892771","title":"Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control","display_name":"Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312564987","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892771"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892771","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"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":"article","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/A5102812354","display_name":"Takuya Kanazawa","orcid":"https://orcid.org/0000-0002-1499-374X"},"institutions":[{"id":"https://openalex.org/I86725329","display_name":"Hitachi Global Storage Technologies (United States)","ror":"https://ror.org/02q0s1x22","country_code":"US","type":"company","lineage":["https://openalex.org/I86725329"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Kanazawa","raw_affiliation_strings":["Hitachi America, Ltd. R&D,Industrial AI Lab,Santa Clara,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi America, Ltd. R&D,Industrial AI Lab,Santa Clara,CA","institution_ids":["https://openalex.org/I86725329"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354470","display_name":"Haiyan Wang","orcid":"https://orcid.org/0000-0003-2815-0978"},"institutions":[{"id":"https://openalex.org/I86725329","display_name":"Hitachi Global Storage Technologies (United States)","ror":"https://ror.org/02q0s1x22","country_code":"US","type":"company","lineage":["https://openalex.org/I86725329"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiyan Wang","raw_affiliation_strings":["Hitachi America, Ltd. R&D,Industrial AI Lab,Santa Clara,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi America, Ltd. R&D,Industrial AI Lab,Santa Clara,CA","institution_ids":["https://openalex.org/I86725329"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103731588","display_name":"Chetan Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I86725329","display_name":"Hitachi Global Storage Technologies (United States)","ror":"https://ror.org/02q0s1x22","country_code":"US","type":"company","lineage":["https://openalex.org/I86725329"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chetan Gupta","raw_affiliation_strings":["Hitachi America, Ltd. R&D,Industrial AI Lab,Santa Clara,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi America, Ltd. R&D,Industrial AI Lab,Santa Clara,CA","institution_ids":["https://openalex.org/I86725329"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86725329"],"apc_list":null,"apc_paid":null,"fwci":0.4152,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59517625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9980000257492065,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7705307006835938},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7554795742034912},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.7327799201011658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6458496451377869},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5581117868423462},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5358266830444336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5286524891853333},{"id":"https://openalex.org/keywords/measurement-uncertainty","display_name":"Measurement uncertainty","score":0.4629109501838684},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.43691718578338623},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4278864562511444},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4008774161338806},{"id":"https://openalex.org/keywords/industrial-engineering","display_name":"Industrial engineering","score":0.34393221139907837},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3262391686439514},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15024089813232422},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14304885268211365}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7705307006835938},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7554795742034912},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.7327799201011658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6458496451377869},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5581117868423462},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5358266830444336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5286524891853333},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.4629109501838684},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.43691718578338623},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4278864562511444},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4008774161338806},{"id":"https://openalex.org/C13736549","wikidata":"https://www.wikidata.org/wiki/Q4489420","display_name":"Industrial engineering","level":1,"score":0.34393221139907837},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3262391686439514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15024089813232422},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14304885268211365},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/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":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892771","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"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":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":117,"referenced_works":["https://openalex.org/W89883662","https://openalex.org/W1551275368","https://openalex.org/W1581437610","https://openalex.org/W1585575029","https://openalex.org/W1647779468","https://openalex.org/W1845972764","https://openalex.org/W1959608418","https://openalex.org/W2041946752","https://openalex.org/W2042816232","https://openalex.org/W2102288976","https://openalex.org/W2111959010","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2280163991","https://openalex.org/W2356031020","https://openalex.org/W2746553466","https://openalex.org/W2765302304","https://openalex.org/W2767313115","https://openalex.org/W2774354230","https://openalex.org/W2778821583","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2795578496","https://openalex.org/W2798705390","https://openalex.org/W2803308811","https://openalex.org/W2807588596","https://openalex.org/W2807908072","https://openalex.org/W2809352054","https://openalex.org/W2811334097","https://openalex.org/W2884674451","https://openalex.org/W2902435472","https://openalex.org/W2902907165","https://openalex.org/W2945850646","https://openalex.org/W2949207039","https://openalex.org/W2951191893","https://openalex.org/W2951873965","https://openalex.org/W2963238274","https://openalex.org/W2963430540","https://openalex.org/W2963864421","https://openalex.org/W2968113041","https://openalex.org/W2979693376","https://openalex.org/W2982238716","https://openalex.org/W2983617607","https://openalex.org/W2986399309","https://openalex.org/W2998059334","https://openalex.org/W2998802444","https://openalex.org/W3014596384","https://openalex.org/W3015082424","https://openalex.org/W3015872947","https://openalex.org/W3021267234","https://openalex.org/W3021619395","https://openalex.org/W3092305369","https://openalex.org/W3102100346","https://openalex.org/W3123216837","https://openalex.org/W3129049248","https://openalex.org/W3134774296","https://openalex.org/W3164731060","https://openalex.org/W3169327131","https://openalex.org/W3172115140","https://openalex.org/W3177161388","https://openalex.org/W3192508890","https://openalex.org/W3196473921","https://openalex.org/W3197610447","https://openalex.org/W3203728584","https://openalex.org/W3206010851","https://openalex.org/W3214951365","https://openalex.org/W4214717370","https://openalex.org/W4230778209","https://openalex.org/W4237591687","https://openalex.org/W4241584625","https://openalex.org/W4286972819","https://openalex.org/W4287017924","https://openalex.org/W4287167695","https://openalex.org/W4287324936","https://openalex.org/W4287810981","https://openalex.org/W4289107544","https://openalex.org/W4298876402","https://openalex.org/W4308170110","https://openalex.org/W6603650463","https://openalex.org/W6634584832","https://openalex.org/W6635327058","https://openalex.org/W6640963894","https://openalex.org/W6675423570","https://openalex.org/W6683300800","https://openalex.org/W6683517036","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6695011786","https://openalex.org/W6706320068","https://openalex.org/W6730042731","https://openalex.org/W6744927671","https://openalex.org/W6746581380","https://openalex.org/W6747231145","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6751629939","https://openalex.org/W6752244597","https://openalex.org/W6752887809","https://openalex.org/W6757560991","https://openalex.org/W6759679099","https://openalex.org/W6762639926","https://openalex.org/W6763305696","https://openalex.org/W6767112054","https://openalex.org/W6767334564","https://openalex.org/W6768581196","https://openalex.org/W6770012831","https://openalex.org/W6773161478","https://openalex.org/W6776730770","https://openalex.org/W6776837600","https://openalex.org/W6780571964","https://openalex.org/W6788575936","https://openalex.org/W6790740607","https://openalex.org/W6800089562","https://openalex.org/W6800099043","https://openalex.org/W6801642106","https://openalex.org/W6803712134","https://openalex.org/W6804566653"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Uncertainty":[0],"quantification":[1],"is":[2],"one":[3],"of":[4,22,39,99],"the":[5,41,69],"central":[6],"challenges":[7],"for":[8,63],"machine":[9],"learning":[10,61],"in":[11,107],"real-world":[12],"applications.":[13],"In":[14,53],"reinforcement":[15,60],"learning,":[16],"an":[17,58],"agent":[18],"confronts":[19],"two":[20],"kinds":[21],"uncertainty,":[23],"called":[24],"epistemic":[25,78],"uncertainty":[26,79,85,105],"and":[27,31,47,83,113],"aleatoric":[28,84],"uncertainty.":[29],"Disentangling":[30],"evaluating":[32],"these":[33],"uncertainties":[34],"simultaneously":[35],"stands":[36],"a":[37,88],"chance":[38],"improving":[40],"agent's":[42],"final":[43],"performance,":[44],"accelerating":[45],"training,":[46],"facilitating":[48],"quality":[49],"assurance":[50],"after":[51],"deployment.":[52],"this":[54],"work,":[55],"we":[56],"propose":[57],"uncertainty-aware":[59],"algorithm":[62,74],"continuous":[64],"control":[65,112],"tasks":[66,109],"that":[67,96],"extends":[68],"Deep":[70],"Deterministic":[71],"Policy":[72],"Gradient":[73],"(DDPG).":[75],"It":[76],"exploits":[77],"to":[80,86],"accelerate":[81],"exploration":[82],"learn":[87],"risk-sensitive":[89],"policy.":[90],"We":[91],"conduct":[92],"numerical":[93],"experiments":[94],"showing":[95],"our":[97],"variant":[98],"DDPG":[100,103],"outperforms":[101],"vanilla":[102],"without":[104],"estimation":[106],"benchmark":[108],"on":[110],"robotic":[111],"power-grid":[114],"optimization.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}