{"id":"https://openalex.org/W7133200328","doi":"https://doi.org/10.52202/075280-0703","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","display_name":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W7133200328","doi":"https://doi.org/10.52202/075280-0703"},"language":"en","primary_location":{"id":"doi:10.52202/075280-0703","doi":"https://doi.org/10.52202/075280-0703","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-0703","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2207.13081","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127838085","display_name":"Masatoshi Uehara","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masatoshi Uehara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001514927","display_name":"Haruka Kiyohara","orcid":"https://orcid.org/0009-0000-6378-4365","observed_orcids":["https://orcid.org/0009-0000-6378-4365"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haruka Kiyohara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127814246","display_name":"Andrew Bennett","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Bennett","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068383641","display_name":"Victor Chernozhukov","orcid":"https://orcid.org/0000-0002-3250-6714","observed_orcids":["https://orcid.org/0000-0002-3250-6714"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Victor Chernozhukov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127847525","display_name":"Nan Jiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036921114","display_name":"Nathan Kallus","orcid":"https://orcid.org/0000-0003-1672-0507","observed_orcids":["https://orcid.org/0000-0003-1672-0507","https://orcid.org/0000-0002-2757-1570"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathan Kallus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025970743","display_name":"Chengchun Shi","orcid":"https://orcid.org/0000-0001-7773-2099","observed_orcids":["https://orcid.org/0000-0001-7773-2099"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengchun Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125707879","display_name":"Wen Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0622,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81119465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"15991","last_page":"16008"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.00019999999494757503,"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":9.999999747378752e-05,"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":0.9580000042915344},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.9169999957084656},{"id":"https://openalex.org/keywords/value-based-methods","display_name":"value-based methods","score":0.7509999871253967},{"id":"https://openalex.org/keywords/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.5350000262260437},{"id":"https://openalex.org/keywords/policy-evaluation","display_name":"policy evaluation","score":0.47099998593330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5830000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36059999465942383},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.23680000007152557},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2353000044822693},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.23489999771118164},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.23149999976158142},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.22689999639987946},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.22439999878406525}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.52202/075280-0703","doi":"https://doi.org/10.52202/075280-0703","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-0703","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2207.13081","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.13081","pdf_url":"https://arxiv.org/pdf/2207.13081","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":"pmh:oai:eprints.lse.ac.uk:122752","doi":null,"is_oa":true,"landing_page_url":"https://orcid.org/0000-0001-7773-2099>","pdf_url":"http://eprints.lse.ac.uk/122752/1/Future_Dependent_Value_Based.pdf","source":{"id":"https://openalex.org/S4306401593","display_name":"London School of Economics and Political Science Research Online (London School of Economics and Political Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I909854389","host_organization_name":"London School of Economics and Political Science","host_organization_lineage":["https://openalex.org/I909854389"],"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":"Book Section"},{"id":"pmh:oai:researchonline.lse.ac.uk:122752","doi":null,"is_oa":true,"landing_page_url":"https://orcid.org/0000-0001-7773-2099>","pdf_url":"https://researchonline.lse.ac.uk/id/eprint/122752/1/Future_Dependent_Value_Based.pdf","source":{"id":"https://openalex.org/S4306400050","display_name":"London School of Economics and Political Science Theses Online (London School of Economics and Political Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I909854389","host_organization_name":"London School of Economics and Political Science","host_organization_lineage":["https://openalex.org/I909854389"],"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":"Chapter"},{"id":"doi:10.48550/arxiv.2207.13081","doi":"https://doi.org/10.48550/arxiv.2207.13081","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2207.13081","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2207.13081","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.13081","pdf_url":"https://arxiv.org/pdf/2207.13081","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/G2186497367","display_name":"AI Institute for Future Edge Networks and Distributed Intelligence (AI-EDGE)","funder_award_id":"2112471","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G288802330","display_name":"CAREER: Robust Policy Learning for Safe and Reliable Algorithmic Decision Making from Observational Data in Sensitive Applications","funder_award_id":"1846210","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3167606647","display_name":"RI: Small: Towards Provably Efficient Representation Learning in Reinforcement Learning via Rich Function Approximation","funder_award_id":"2154711","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3806070367","display_name":"Statistical Methods in Offline Reinforcement Learning","funder_award_id":"EP/W014971/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G979841810","display_name":"CAREER: Theoretical Foundations of Offline Reinforcement Learning","funder_award_id":"2141781","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"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415795361","https://openalex.org/W3212427392","https://openalex.org/W7133243105","https://openalex.org/W4415084288","https://openalex.org/W7103235586","https://openalex.org/W3200722136","https://openalex.org/W4409158543","https://openalex.org/W7133517527","https://openalex.org/W3210893445","https://openalex.org/W2804152667"],"abstract_inverted_index":{"We":[0,68,89,106],"study":[1],"off-policy":[2],"evaluation":[3,24],"(OPE)":[4],"for":[5,74],"partially":[6],"observable":[7],"MDPs":[8],"(POMDPs)":[9],"with":[10],"general":[11],"function":[12],"approximation.":[13],"Existing":[14],"methods":[15,138,155],"such":[16],"as":[17,53,61,78,86,118,120],"sequential":[18],"importance":[19],"sampling":[20],"estimators":[21],"and":[22,122,130,143,150],"fitted-Q":[23],"suffer":[25],"from":[26],"the":[27,102,108,131,145,151],"curse":[28],"of":[29,141],"horizon":[30],"in":[31,65,156],"POMDPs.":[32,157],"To":[33],"circumvent":[34],"this":[35],"problem,":[36],"we":[37,135],"develop":[38],"a":[39,70,92],"novel":[40],"model-free":[41],"OPE":[42,114],"method":[43,95],"by":[44],"introducing":[45],"future-dependent":[46,75,98],"value":[47,56,63,76,99],"functions":[48,57,64,77,100],"that":[49,82],"take":[50],"future":[51],"proxies":[52,85],"inputs.":[54],"Future-dependent":[55],"play":[58],"similar":[59],"roles":[60],"classical":[62],"fully-observable":[66],"MDPs.":[67],"derive":[69],"new":[71,103],"Bellman":[72,104,132],"equation":[73],"conditional":[79],"moment":[80],"equations":[81],"use":[83],"history":[84],"instrumental":[87],"variables.":[88],"further":[90],"propose":[91],"minimax":[93],"learning":[94,140,154],"to":[96,139],"learn":[97],"using":[101],"equation.":[105],"obtain":[107],"PAC":[109],"result,":[110],"which":[111],"implies":[112],"our":[113,137,148],"estimator":[115],"is":[116],"consistent":[117],"long":[119],"futures":[121],"histories":[123],"contain":[124],"sufficient":[125],"information":[126],"about":[127],"latent":[128],"states,":[129],"completeness.":[133],"Finally,":[134],"extend":[136],"dynamics":[142],"establish":[144],"connection":[146],"between":[147],"approach":[149],"well-known":[152],"spectral":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-03-03T00:00:00"}