{"id":"https://openalex.org/W7133243105","doi":"https://doi.org/10.52202/068431-0043","title":"Off-Policy Evaluation for Episodic Partially Observable Markov Decision Processes Under Non-Parametric Models","display_name":"Off-Policy Evaluation for Episodic Partially Observable Markov Decision Processes Under Non-Parametric Models","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W7133243105","doi":"https://doi.org/10.52202/068431-0043"},"language":"en","primary_location":{"id":"doi:10.52202/068431-0043","doi":"https://doi.org/10.52202/068431-0043","is_oa":false,"landing_page_url":"https://doi.org/10.52202/068431-0043","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 35","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/2209.10064","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127804794","display_name":"Rui Miao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Miao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127852587","display_name":"Zhengling Qi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengling Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127788931","display_name":"Xiaoke Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoke Zhang","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":0.1382,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44324261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"593","last_page":"606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9897000193595886,"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":0.9897000193595886,"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":0.002400000113993883,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0020000000949949026,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/off-policy-evaluation","display_name":"off-policy evaluation","score":1.0},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.9800000190734863},{"id":"https://openalex.org/keywords/nonparametric-models","display_name":"nonparametric models","score":0.9020000100135803},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.46299999952316284},{"id":"https://openalex.org/keywords/policy-evaluation","display_name":"policy evaluation","score":0.3310000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.555899977684021},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.49639999866485596},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.39419999718666077},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3594000041484833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3163999915122986},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3068999946117401},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C186116695","wikidata":"https://www.wikidata.org/wiki/Q5249226","display_name":"Decision analysis","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/068431-0043","doi":"https://doi.org/10.52202/068431-0043","is_oa":false,"landing_page_url":"https://doi.org/10.52202/068431-0043","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 35","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2209.10064","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.10064","pdf_url":"https://arxiv.org/pdf/2209.10064","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.2209.10064","doi":"https://doi.org/10.48550/arxiv.2209.10064","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.10064","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:2209.10064","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.10064","pdf_url":"https://arxiv.org/pdf/2209.10064","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3212427392","https://openalex.org/W7103235586","https://openalex.org/W4415795361","https://openalex.org/W3210893445","https://openalex.org/W4225675157","https://openalex.org/W7133200328","https://openalex.org/W4415020600","https://openalex.org/W2804152667","https://openalex.org/W4313447125","https://openalex.org/W2971972375"],"abstract_inverted_index":{"We":[0,53],"study":[1],"the":[2,21,36,47,85,91,99,105,121,128],"problem":[3,70],"of":[4,42,49,104,109,115,123],"off-policy":[5],"evaluation":[6],"(OPE)":[7],"for":[8,34,89,97,133],"episodic":[9],"Partially":[10],"Observable":[11],"Markov":[12],"Decision":[13],"Processes":[14],"(POMDPs)":[15],"with":[16,46],"continuous":[17],"states.":[18],"Motivated":[19],"by":[20],"recently":[22],"proposed":[23],"proximal":[24],"causal":[25],"inference":[26],"framework,":[27],"we":[28,83],"develop":[29,55],"a":[30,40,56,65],"non-parametric":[31,66,138],"identification":[32],"result":[33],"estimating":[35,90],"policy":[37,100],"value":[38],"via":[39],"sequence":[41],"so-called":[43,112],"V-bridge":[44,61,92],"functions":[45,62,93],"help":[48],"time-dependent":[50],"proxy":[51],"variables.":[52],"then":[54],"fitted-Q-evaluation-type":[57],"algorithm":[58],"to":[59],"estimate":[60],"recursively,":[63],"where":[64],"instrumental":[67],"variable":[68],"(NPIV)":[69],"is":[71,127],"solved":[72],"at":[73,117],"each":[74,118],"step.":[75,119],"By":[76],"analyzing":[77],"this":[78,126],"challenging":[79],"sequential":[80],"NPIV":[81],"problem,":[82],"establish":[84],"finite-sample":[86,130],"error":[87,131],"bounds":[88],"and":[94,111],"accordingly":[95],"that":[96],"evaluating":[98],"value,":[101],"in":[102,135],"terms":[103],"sample":[106],"size,":[107],"length":[108],"horizon":[110],"(local)":[113],"measure":[114],"ill-posedness":[116],"To":[120],"best":[122],"our":[124],"knowledge,":[125],"first":[129],"bound":[132],"OPE":[134],"POMDPs":[136],"under":[137],"models.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-03-03T00:00:00"}