{"id":"https://openalex.org/W7214806254","doi":"https://doi.org/10.48550/arxiv.2609.34593","title":"Deep Weighted Bellman Residual Minimization for $Q^*$ Estimation","display_name":"Deep Weighted Bellman Residual Minimization for $Q^*$ Estimation","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214806254","doi":"https://doi.org/10.48550/arxiv.2609.34593"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.34593","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34593","pdf_url":"https://arxiv.org/pdf/2609.34593","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.34593","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086788173","display_name":"Lican Kang","orcid":"https://orcid.org/0000-0003-3136-9225","observed_orcids":["https://orcid.org/0000-0003-3136-9225"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang, Lican","raw_affiliation_strings":["Hubei Key Laboratory of Computational Science , Wuhan University , Wuhan , 430072 , China","Institute for Math and AI , Wuhan University , Wuhan , 430072 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Computational Science , Wuhan University , Wuhan , 430072 , China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Institute for Math and AI , Wuhan University , Wuhan , 430072 , China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057896052","display_name":"Jerry Zhijian Yang","orcid":"https://orcid.org/0000-0002-0402-4056","observed_orcids":["https://orcid.org/0000-0002-0402-4056"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jerry Zhijian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153445240","display_name":"Cheng Yuan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan, Cheng","raw_affiliation_strings":["Hubei Key Laboratory of Computational Science , Wuhan University , Wuhan , 430072 , China","School of Artificial Intelligence , Wuhan University , Wuhan , 430072 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Computational Science , Wuhan University , Wuhan , 430072 , China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Artificial Intelligence , Wuhan University , Wuhan , 430072 , China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5146065348","display_name":"Chen Zhong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong, Chen","raw_affiliation_strings":["School of Mathematics and Statistics , Wuhan University , Wuhan , 430072 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics , Wuhan University , Wuhan , 430072 , China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/off-policy-evaluation","display_name":"off-policy evaluation","score":0.9810000061988831},{"id":"https://openalex.org/keywords/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.9629999995231628},{"id":"https://openalex.org/keywords/q-estimation","display_name":"Q estimation","score":0.6970000267028809},{"id":"https://openalex.org/keywords/expert-demonstrations","display_name":"expert demonstrations","score":0.8270000219345093},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.8159999847412109},{"id":"https://openalex.org/keywords/q-value-overestimation","display_name":"Q-value overestimation","score":0.9710000157356262},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.7319999933242798},{"id":"https://openalex.org/keywords/excess-risk","display_name":"excess risk","score":0.8999999761581421},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.5580000281333923},{"id":"https://openalex.org/keywords/policy-generalization","display_name":"policy generalization","score":0.7599999904632568}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8080000281333923},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6830000281333923},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.6514999866485596},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6306999921798706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5511000156402588},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5317999720573425},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.48899999260902405},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.3813000023365021},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32170000672340393},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.32120001316070557},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26019999384880066}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.34593","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34593","pdf_url":"https://arxiv.org/pdf/2609.34593","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.34593","doi":"https://doi.org/10.48550/arxiv.2609.34593","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.34593","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.34593","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34593","pdf_url":"https://arxiv.org/pdf/2609.34593","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5448272545","display_name":null,"funder_award_id":"12301558","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6616829470","display_name":null,"funder_award_id":"No. 12125103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8797177794","display_name":null,"funder_award_id":"12125103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214806254.pdf","grobid_xml":"https://content.openalex.org/works/W7214806254.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7203650104","https://openalex.org/W2981972696","https://openalex.org/W4387819073","https://openalex.org/W3133661462","https://openalex.org/W7160637272","https://openalex.org/W7148729830","https://openalex.org/W4281700675","https://openalex.org/W6889779352","https://openalex.org/W3163990682","https://openalex.org/W7155246629"],"abstract_inverted_index":{"Off-policy":[0],"evaluation":[1],"is":[2],"a":[3,45,86],"foundational":[4],"component":[5],"of":[6,80,103,135],"offline":[7],"reinforcement":[8,82],"learning,":[9],"aiming":[10],"to":[11,114],"assess":[12],"and":[13,33,94,125],"optimize":[14],"policy":[15,126],"performance":[16,124],"using":[17],"pre-collected":[18],"datasets.":[19],"However,":[20],"such":[21],"datasets":[22],"often":[23],"suffer":[24],"from":[25,69],"pronounced":[26],"challenges,":[27],"including":[28],"distribution":[29],"shift,":[30],"$Q$-value":[31],"overestimation,":[32],"low":[34],"sample":[35],"utilization":[36,134],"efficiency.":[37],"To":[38],"address":[39],"these":[40],"issues,":[41],"this":[42],"paper":[43],"introduces":[44],"weighted":[46],"Bellman":[47],"residual":[48],"minimization":[49],"framework":[50],"that":[51],"incorporates":[52],"density":[53,91],"ratio":[54,92],"weighting":[55,66],"by":[56],"effectively":[57],"integrating":[58],"expert":[59,136],"demonstrations":[60],"with":[61],"behavioral":[62],"data.":[63],"The":[64],"proposed":[65],"scheme":[67],"departs":[68],"the":[70,77,96,100,132],"conventional":[71],"completeness":[72],"assumption":[73],"commonly":[74],"imposed":[75],"in":[76,122],"theoretical":[78],"analysis":[79],"deep":[81,105],"learning.":[83],"We":[84],"establish":[85],"sharp":[87],"convergence":[88,97],"rate":[89,98],"for":[90,99,131],"estimation":[93],"derive":[95],"excess":[101],"risk":[102],"resulting":[104],"$Q^*$":[106],"estimator.":[107],"Extensive":[108],"empirical":[109],"evaluations":[110],"demonstrate":[111],"that,":[112],"compared":[113],"existing":[115],"methods,":[116],"our":[117],"method":[118],"achieves":[119],"significant":[120],"improvements":[121],"numerical":[123],"generalization,":[127],"providing":[128],"specific":[129],"guidance":[130],"rational":[133],"demonstrations.":[137]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-09-30T00:00:00"}