{"id":"https://openalex.org/W4408056770","doi":"https://doi.org/10.1142/s0218001425510012","title":"Bayesian Uncertainty Weighted Optimization for Offline Reinforcement Learning","display_name":"Bayesian Uncertainty Weighted Optimization for Offline Reinforcement Learning","publication_year":2025,"publication_date":"2025-03-01","ids":{"openalex":"https://openalex.org/W4408056770","doi":"https://doi.org/10.1142/s0218001425510012"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001425510012","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001425510012","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-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/A5100460612","display_name":"Tianyi Li","orcid":"https://orcid.org/0009-0001-3265-9921"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyi Li","raw_affiliation_strings":["Ningbo Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200030, P.\u00a0R.\u00a0China"],"affiliations":[{"raw_affiliation_string":"Ningbo Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200030, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Genke Yang","orcid":"https://orcid.org/0000-0003-3492-0211"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Genke Yang","raw_affiliation_strings":["Ningbo Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200030, P.\u00a0R.\u00a0China"],"affiliations":[{"raw_affiliation_string":"Ningbo Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200030, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001657537","display_name":"Jian Chu","orcid":"https://orcid.org/0000-0003-1404-1834"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Chu","raw_affiliation_strings":["Ningbo Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200030, P.\u00a0R.\u00a0China"],"affiliations":[{"raw_affiliation_string":"Ningbo Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai 200030, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100460612"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03866397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"06","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9336000084877014,"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"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9336000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7275601625442505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6980969309806824},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6069157719612122},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5931226015090942},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5355358719825745},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.5055489540100098}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7275601625442505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6980969309806824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6069157719612122},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5931226015090942},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5355358719825745},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.5055489540100098}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001425510012","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001425510012","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2766447205","https://openalex.org/W3018036994","https://openalex.org/W3024191488","https://openalex.org/W3092253573","https://openalex.org/W3118420573","https://openalex.org/W3119430426","https://openalex.org/W3127561923","https://openalex.org/W3135025188","https://openalex.org/W3138939485","https://openalex.org/W3164394845","https://openalex.org/W3169375224","https://openalex.org/W3207882166","https://openalex.org/W4206024271","https://openalex.org/W4223423981","https://openalex.org/W4224990480","https://openalex.org/W4225150561","https://openalex.org/W4290422707","https://openalex.org/W4297020691","https://openalex.org/W4311607213","https://openalex.org/W4312281895","https://openalex.org/W4312650890","https://openalex.org/W4322730848","https://openalex.org/W4360584316","https://openalex.org/W4362471974","https://openalex.org/W4383112908","https://openalex.org/W4385664721","https://openalex.org/W4385938565","https://openalex.org/W4386238548","https://openalex.org/W4387018580","https://openalex.org/W4388181063","https://openalex.org/W4388822849","https://openalex.org/W4393937654","https://openalex.org/W4395680426"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"(offline":[3],"RL)":[4],"endeavors":[5],"to":[6,59,64,116],"learn":[7],"effective":[8,53],"policies":[9],"from":[10,29,39],"a":[11,50],"large":[12],"batch":[13],"of":[14],"pre-collected":[15],"datasets":[16],"without":[17,111],"any":[18],"costly":[19],"or":[20,43],"dangerous":[21],"online":[22],"exploration.":[23],"Nevertheless,":[24],"offline":[25,89],"RL":[26,90],"always":[27],"suffers":[28],"substantial":[30],"algorithmic":[31],"extrapolation":[32],"errors":[33],"and":[34,52,75],"may":[35],"fail":[36],"when":[37],"bootstrapping":[38],"out-of-distribution":[40],"(OOD)":[41],"actions":[42],"states.":[44],"In":[45],"this":[46],"work,":[47],"we":[48],"introduce":[49],"practical":[51],"Bayesian":[54,62],"uncertainty":[55,63,69],"weighted":[56],"optimization":[57],"(BUWO)":[58],"leverage":[60],"the":[61,67,77,100,104,117],"account":[65],"for":[66],"epistemic":[68],"associated":[70],"with":[71,80,86],"each":[72],"training":[73],"sample":[74],"penalize":[76],"state-action":[78],"pairs":[79],"high":[81],"uncertainty.":[82],"We":[83],"compare":[84],"BUWO":[85],"other":[87],"prevailing":[88],"algorithms":[91],"on":[92],"D4RL":[93],"benchmarks.":[94],"The":[95],"experimental":[96],"results":[97],"demonstrate":[98],"that":[99],"algorithm":[101],"can":[102],"enhance":[103],"average":[105],"reward":[106],"score":[107],"by":[108],"almost":[109],"15%":[110],"additional":[112],"computational":[113],"costs":[114],"compared":[115],"current":[118],"state-of-the-art":[119],"algorithm.":[120]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}