{"id":"https://openalex.org/W4390099537","doi":"https://doi.org/10.1109/robio58561.2023.10354785","title":"Uncertainty in Bayesian Reinforcement Learning for Robot Manipulation Tasks with Sparse Rewards","display_name":"Uncertainty in Bayesian Reinforcement Learning for Robot Manipulation Tasks with Sparse Rewards","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4390099537","doi":"https://doi.org/10.1109/robio58561.2023.10354785"},"language":"en","primary_location":{"id":"doi:10.1109/robio58561.2023.10354785","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio58561.2023.10354785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5100600010","display_name":"Li Zheng","orcid":"https://orcid.org/0009-0005-7582-6995"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Zheng","raw_affiliation_strings":["University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106550899","display_name":"Yanghong Li","orcid":"https://orcid.org/0000-0002-8974-6524"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanghong Li","raw_affiliation_strings":["University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101917478","display_name":"Yahao Wang","orcid":"https://orcid.org/0000-0002-3323-4968"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahao Wang","raw_affiliation_strings":["University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056554020","display_name":"Guangrui Bai","orcid":"https://orcid.org/0000-0002-0002-8121"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangrui Bai","raw_affiliation_strings":["University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101189452","display_name":"Haiyang He","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang He","raw_affiliation_strings":["University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091526893","display_name":"Erbao Dong","orcid":"https://orcid.org/0000-0002-4062-9730"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Erbao Dong","raw_affiliation_strings":["University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100600010"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.5245,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72993979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9549999833106995,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8237442970275879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733486533164978},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.7192149758338928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6945873498916626},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5787407159805298},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5184247493743896},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5182292461395264},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5019323825836182},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.46165478229522705},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4505487084388733},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.43844375014305115}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8237442970275879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733486533164978},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.7192149758338928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6945873498916626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5787407159805298},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5184247493743896},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5182292461395264},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5019323825836182},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.46165478229522705},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4505487084388733},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.43844375014305115},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio58561.2023.10354785","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio58561.2023.10354785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":19,"referenced_works":["https://openalex.org/W1965770722","https://openalex.org/W2047229728","https://openalex.org/W2344786740","https://openalex.org/W2736601468","https://openalex.org/W2951625652","https://openalex.org/W2963906246","https://openalex.org/W2973229164","https://openalex.org/W2982316857","https://openalex.org/W3127561923","https://openalex.org/W4285506274","https://openalex.org/W4287209565","https://openalex.org/W4293872189","https://openalex.org/W4361002041","https://openalex.org/W6684488266","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748599296","https://openalex.org/W6748839928","https://openalex.org/W6793853427"],"related_works":["https://openalex.org/W2407375987","https://openalex.org/W3049691116","https://openalex.org/W2505726097","https://openalex.org/W2010643158","https://openalex.org/W2106867672","https://openalex.org/W3081214562","https://openalex.org/W4310268968","https://openalex.org/W2950975704","https://openalex.org/W4297815943","https://openalex.org/W2053745677"],"abstract_inverted_index":{"This":[0],"paper":[1,53],"aims":[2],"to":[3,69],"explore":[4],"the":[5,23,42,71,82,90,116,121,127,131,140],"application":[6],"of":[7,44,89,101,130],"Bayesian":[8,67,122],"deep":[9,32],"reinforcement":[10,33,63],"learning":[11,34,64],"(BDRL)":[12],"in":[13,25,41,76,81,133],"robot":[14,45],"manipulation":[15,46],"tasks":[16,136],"with":[17,66],"sparse":[18,134],"rewards,":[19],"focusing":[20],"on":[21,98,120],"addressing":[22],"uncertainty":[24,75,80],"complex":[26],"and":[27,79,87],"sparsely":[28,103],"rewarded":[29,104],"environments.":[30],"Conventional":[31],"(DRL)":[35],"algorithms":[36,65,132],"still":[37],"face":[38],"significant":[39],"challenges":[40],"context":[43],"tasks.":[47],"To":[48],"address":[49],"this":[50,52],"issue,":[51],"proposes":[54],"a":[55],"general":[56],"algorithm":[57,92,118],"framework":[58],"called":[59],"BDRL":[60],"that":[61,115],"combines":[62],"networks":[68],"quantify":[70],"model":[72,141],"uncertainty,":[73],"aleatoric":[74],"neural":[77],"networks,":[78],"reward":[83,135],"function.":[84],"The":[85,111],"effectiveness":[86],"generality":[88],"proposed":[91],"are":[93],"validated":[94],"through":[95],"simulation":[96],"experiments":[97],"multiple":[99],"sets":[100],"different":[102],"tasks,":[105],"employing":[106],"various":[107],"advanced":[108],"DRL":[109,117],"algorithms.":[110],"research":[112],"results":[113],"demonstrate":[114],"based":[119],"network":[123],"mechanism":[124],"significantly":[125],"improves":[126],"convergence":[128],"speed":[129],"by":[137],"accurately":[138],"estimating":[139],"uncertainty.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}