{"id":"https://openalex.org/W4387322993","doi":"https://doi.org/10.48550/arxiv.2310.01380","title":"Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning","display_name":"Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning","publication_year":2023,"publication_date":"2023-10-02","ids":{"openalex":"https://openalex.org/W4387322993","doi":"https://doi.org/10.48550/arxiv.2310.01380"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.01380","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.01380","pdf_url":"https://arxiv.org/pdf/2310.01380","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.01380","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113779780","display_name":"Qiwei Di","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di, Qiwei","raw_affiliation_strings":["Department of Computer Science , University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063820180","display_name":"Heyang Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao, Heyang","raw_affiliation_strings":["Department of Computer Science , University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101300665","display_name":"Jiafan He","orcid":"https://orcid.org/0009-0008-0815-5783","observed_orcids":["https://orcid.org/0009-0008-0815-5783"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He, Jiafan","raw_affiliation_strings":["Department of Computer Science , University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051448391","display_name":"Quanquan Gu","orcid":"https://orcid.org/0000-0001-9830-793X","observed_orcids":["https://orcid.org/0000-0001-9830-793X"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gu, Quanquan","raw_affiliation_strings":["Department of Computer Science , University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"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":0.9955999851226807,"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":0.9955999851226807,"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":0.004000000189989805,"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/T12072","display_name":"Machine Learning and Algorithms","score":9.999999747378752e-05,"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/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":1.0},{"id":"https://openalex.org/keywords/nonlinear-function-approximation","display_name":"nonlinear function approximation","score":0.7730000019073486},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.6959999799728394},{"id":"https://openalex.org/keywords/variance-estimation","display_name":"variance estimation","score":0.9480000138282776},{"id":"https://openalex.org/keywords/minimax-optimality","display_name":"minimax optimality","score":0.6759999990463257},{"id":"https://openalex.org/keywords/planning-stage","display_name":"planning phase","score":0.3889999985694885}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6835911273956299},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6617290377616882},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.6463906764984131},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5363762378692627},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5296787023544312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5017249584197998},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49964475631713867},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.47835344076156616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3960036039352417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1829548180103302},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1598166823387146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10020533204078674},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09986111521720886},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.09387531876564026},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.01380","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.01380","pdf_url":"https://arxiv.org/pdf/2310.01380","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.2310.01380","doi":"https://doi.org/10.48550/arxiv.2310.01380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.01380","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.01380","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.01380","pdf_url":"https://arxiv.org/pdf/2310.01380","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/G5222657029","display_name":"CPS: Medium: Collaborative Research: Provably Safe and Robust Multi-Agent Reinforcement Learning with Applications in Urban Air Mobility","funder_award_id":"2312094","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6024092204","display_name":"CAREER:  Scaling Up Knowledge Discovery in High-Dimensional Data Via Nonconvex Statistical Optimization","funder_award_id":"1906169","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387322993.pdf","grobid_xml":"https://content.openalex.org/works/W4387322993.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2979895842","https://openalex.org/W3094261094","https://openalex.org/W3169790170","https://openalex.org/W4221155771","https://openalex.org/W4225838216","https://openalex.org/W4283011016","https://openalex.org/W4311432352","https://openalex.org/W4392591475","https://openalex.org/W7133223173"],"related_works":["https://openalex.org/W4221155771","https://openalex.org/W4382203515","https://openalex.org/W4322718377","https://openalex.org/W4404108856","https://openalex.org/W4318719464","https://openalex.org/W3114509039","https://openalex.org/W4302011905","https://openalex.org/W3211766091","https://openalex.org/W4311432277","https://openalex.org/W6980865263"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"(RL),":[3],"where":[4],"the":[5,10,15,149,168],"agent":[6],"aims":[7],"to":[8,52,112,161,182],"learn":[9],"optimal":[11,41,156],"policy":[12],"based":[13],"on":[14,62,148],"data":[16],"collected":[17],"by":[18],"a":[19,103,113,120,127,132,140,145,183],"behavior":[20],"policy,":[21],"has":[22,36,144],"attracted":[23],"increasing":[24],"attention":[25],"in":[26],"recent":[27],"years.":[28],"While":[29],"offline":[30,53,63,89],"RL":[31,54,64,90],"with":[32,40,55,65,91],"linear":[33,162,178],"function":[34,57,67,93,117,150,163,174,181],"approximation":[35,68],"been":[37],"extensively":[38],"studied":[39],"results":[42,171],"achieved":[43],"under":[44],"certain":[45],"assumptions,":[46],"many":[47],"works":[48,61],"shift":[49],"their":[50],"interest":[51],"non-linear":[56,66,92],"approximation.":[58,94,164],"However,":[59],"limited":[60],"have":[69],"instance-dependent":[70,157,170],"regret":[71,141,158],"guarantees.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"propose":[77],"an":[78],"oracle-efficient":[79],"algorithm,":[80],"dubbed":[81],"Pessimistic":[82],"Nonlinear":[83],"Least-Square":[84],"Value":[85],"Iteration":[86],"(PNLSVI),":[87],"for":[88,122],"Our":[95,137,165],"algorithmic":[96],"design":[97],"comprises":[98],"three":[99],"innovative":[100],"components:":[101],"(1)":[102],"variance-based":[104],"weighted":[105],"regression":[106],"scheme":[107],"that":[108,130,143],"can":[109],"be":[110],"applied":[111],"wide":[114],"range":[115],"of":[116],"classes,":[118,175],"(2)":[119],"subroutine":[121],"variance":[123],"estimation,":[124],"and":[125,153,179],"(3)":[126],"planning":[128],"phase":[129],"utilizes":[131],"pessimistic":[133],"value":[134],"iteration":[135],"approach.":[136],"algorithm":[138],"enjoys":[139],"bound":[142],"tight":[146],"dependency":[147],"class":[151],"complexity":[152],"achieves":[154],"minimax":[155],"when":[159],"specialized":[160],"work":[166],"extends":[167],"previous":[169],"within":[172],"simpler":[173],"such":[176],"as":[177],"differentiable":[180],"more":[184],"general":[185],"framework.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-10-04T00:00:00"}