{"id":"https://openalex.org/W4297098337","doi":"https://doi.org/10.1109/jcc56315.2022.00008","title":"Uncertainty Estimation based Intrinsic Reward For Efficient Reinforcement Learning","display_name":"Uncertainty Estimation based Intrinsic Reward For Efficient Reinforcement Learning","publication_year":2022,"publication_date":"2022-08-01","ids":{"openalex":"https://openalex.org/W4297098337","doi":"https://doi.org/10.1109/jcc56315.2022.00008"},"language":"en","primary_location":{"id":"doi:10.1109/jcc56315.2022.00008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcc56315.2022.00008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Joint Cloud Computing (JCC)","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/A5100669320","display_name":"Chao Chen","orcid":"https://orcid.org/0009-0000-4765-2397"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Chen","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061252955","display_name":"Tianjiao Wan","orcid":"https://orcid.org/0000-0002-2423-4982"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianjiao Wan","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023989290","display_name":"Peichang Shi","orcid":"https://orcid.org/0000-0002-0973-7899"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peichang Shi","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088885490","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0002-1236-8318"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016262505","display_name":"Zijian Gao","orcid":"https://orcid.org/0000-0001-5151-3381"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Gao","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Feng","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"34","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":0.9998000264167786,"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":0.9998000264167786,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9919999837875366,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9912999868392944,"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":0.7937963008880615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7483488917350769},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7109405994415283},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.6781452298164368},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6241022348403931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6059415936470032},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5979453921318054},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4941003620624542},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44888439774513245},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.4376484155654907},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14652925729751587},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09614890813827515}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7937963008880615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483488917350769},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7109405994415283},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.6781452298164368},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6241022348403931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6059415936470032},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5979453921318054},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4941003620624542},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44888439774513245},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.4376484155654907},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14652925729751587},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09614890813827515},{"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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcc56315.2022.00008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcc56315.2022.00008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Joint Cloud Computing (JCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W582134693","https://openalex.org/W1246301972","https://openalex.org/W1480053368","https://openalex.org/W1534477342","https://openalex.org/W1866206747","https://openalex.org/W2095705004","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2170899200","https://openalex.org/W2257979135","https://openalex.org/W2559655401","https://openalex.org/W2560185252","https://openalex.org/W2761873684","https://openalex.org/W2791797404","https://openalex.org/W2950794298","https://openalex.org/W2953772919","https://openalex.org/W2963238274","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964067469","https://openalex.org/W2982316857","https://openalex.org/W3036619998","https://openalex.org/W3167112175","https://openalex.org/W3172115140","https://openalex.org/W3214229832","https://openalex.org/W4214717370","https://openalex.org/W4221161302","https://openalex.org/W4286891004","https://openalex.org/W4287724327","https://openalex.org/W4287811291","https://openalex.org/W6600213771","https://openalex.org/W6617145748","https://openalex.org/W6628764021","https://openalex.org/W6632075054","https://openalex.org/W6639216784","https://openalex.org/W6674330103","https://openalex.org/W6684921986","https://openalex.org/W6730042731","https://openalex.org/W6735865323","https://openalex.org/W6756303580","https://openalex.org/W6762863188","https://openalex.org/W6780470247","https://openalex.org/W6780571964","https://openalex.org/W6787713516","https://openalex.org/W6791194670","https://openalex.org/W6796667233","https://openalex.org/W6803067813","https://openalex.org/W6809799041"],"related_works":["https://openalex.org/W3170628611","https://openalex.org/W3022038857","https://openalex.org/W1970537494","https://openalex.org/W3203000071","https://openalex.org/W3141495010","https://openalex.org/W4280592718","https://openalex.org/W4248006826","https://openalex.org/W3095449511","https://openalex.org/W4293575545","https://openalex.org/W2904145923"],"abstract_inverted_index":{"For":[0],"reinforcement":[1],"learning,":[2],"the":[3,11,28,36,46,58,73,84,97,103,107,117],"extrinsic":[4],"reward":[5,95],"is":[6,147],"a":[7,127,140],"core":[8],"factor":[9],"for":[10,109],"learning":[12],"process":[13],"which":[14],"however":[15],"can":[16,50],"be":[17],"very":[18],"sparse":[19],"or":[20],"completely":[21],"missing.":[22],"In":[23,79],"response,":[24],"researchers":[25],"have":[26],"proposed":[27],"idea":[29],"of":[30,60,99,129],"intrinsic":[31,94],"reward,":[32],"such":[33],"as":[34],"encouraging":[35],"agent":[37],"to":[38,92,105],"visit":[39],"novel":[40],"states":[41],"through":[42],"prediction":[43,48],"error.":[44],"However,":[45],"deep":[47,66],"model":[49],"provide":[51],"over-confident":[52],"and":[53,68,76,146,158],"miscalibrated":[54],"predictions.":[55],"To":[56],"mitigate":[57],"impact":[59],"inaccurate":[61],"prediction,":[62],"previous":[63],"research":[64],"applied":[65],"ensembles":[67],"achieved":[69],"superior":[70,114],"results,":[71],"despite":[72],"increased":[74],"computation":[75],"storage":[77,159],"space.":[78,160],"this":[80],"paper,":[81],"inspired":[82],"by":[83],"uncertainty":[85,100],"estimation,":[86],"we":[87,122],"leverage":[88],"Monte":[89],"Carlo":[90],"Dropout":[91],"generate":[93],"from":[96],"perspective":[98],"estimation":[101],"with":[102],"goal":[104],"decrease":[106],"demands":[108],"computing":[110,156],"resources":[111,157],"while":[112,152],"retaining":[113],"performance.":[115],"Utilizing":[116],"simple":[118],"yet":[119],"effective":[120],"approach,":[121],"conduct":[123],"extensive":[124],"experiments":[125],"across":[126],"variety":[128],"benchmark":[130],"environments.":[131],"The":[132],"experimental":[133],"results":[134],"suggest":[135],"that":[136],"our":[137],"method":[138],"provides":[139],"competitive":[141],"performance":[142],"in":[143,149],"final":[144],"score":[145],"faster":[148],"running":[150],"speed,":[151],"requiring":[153],"much":[154],"fewer":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}