{"id":"https://openalex.org/W2946845352","doi":"https://doi.org/10.48550/arxiv.1905.13167","title":"Defining Admissible Rewards for High Confidence Policy Evaluation","display_name":"Defining Admissible Rewards for High Confidence Policy Evaluation","publication_year":2019,"publication_date":"2019-05-30","ids":{"openalex":"https://openalex.org/W2946845352","doi":"https://doi.org/10.48550/arxiv.1905.13167","mag":"2946845352"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1905.13167","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.13167","pdf_url":"https://arxiv.org/pdf/1905.13167","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/1905.13167","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009328512","display_name":"Niranjani Prasad","orcid":"https://orcid.org/0000-0002-6677-280X","observed_orcids":["https://orcid.org/0000-0002-6677-280X"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasad, Niranjani","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065136437","display_name":"Barbara Elizabeth Engelhardt","orcid":"https://orcid.org/0000-0002-6139-7334","observed_orcids":["https://orcid.org/0000-0002-6139-7334"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Engelhardt, Barbara E","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038771285","display_name":"Finale Doshi\u2010Velez","orcid":"https://orcid.org/0000-0003-2886-3898","observed_orcids":["https://orcid.org/0000-0003-2886-3898"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Doshi-Velez, Finale","raw_affiliation_strings":["Harvard University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.7009999752044678},{"id":"https://openalex.org/keywords/off-policy-evaluation","display_name":"off-policy evaluation","score":0.8629999756813049},{"id":"https://openalex.org/keywords/batch-data","display_name":"batch data","score":0.6230000257492065},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.4699999988079071},{"id":"https://openalex.org/keywords/policy-evaluation","display_name":"policy evaluation","score":0.3919999897480011},{"id":"https://openalex.org/keywords/weaning-from-mechanical-ventilation","display_name":"weaning from mechanical ventilation","score":0.7310000061988831},{"id":"https://openalex.org/keywords/critical-care","display_name":"intensive care","score":0.7730000019073486},{"id":"https://openalex.org/keywords/clinical-decision-support","display_name":"clinical decision support","score":0.515999972820282},{"id":"https://openalex.org/keywords/high-risk-settings","display_name":"high-risk settings","score":0.45399999618530273}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.657666802406311},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6472777724266052},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6325479745864868},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5922463536262512},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5830312967300415},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5307260751724243},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5006396770477295},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.48564162850379944},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36102789640426636},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3354480266571045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33055412769317627},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32396551966667175},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.259040892124176},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.18340474367141724},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.1754145324230194},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14061260223388672},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13265833258628845},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.07203540205955505},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1905.13167","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.13167","pdf_url":"https://arxiv.org/pdf/1905.13167","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.1905.13167","doi":"https://doi.org/10.48550/arxiv.1905.13167","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.13167","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:1905.13167","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.13167","pdf_url":"https://arxiv.org/pdf/1905.13167","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":24,"referenced_works":["https://openalex.org/W88199814","https://openalex.org/W745775011","https://openalex.org/W1514587017","https://openalex.org/W1786332878","https://openalex.org/W1931027396","https://openalex.org/W1999874108","https://openalex.org/W2120346334","https://openalex.org/W2135721773","https://openalex.org/W2135995480","https://openalex.org/W2169401877","https://openalex.org/W2273088453","https://openalex.org/W2396881363","https://openalex.org/W2472245206","https://openalex.org/W2573422763","https://openalex.org/W2609169452","https://openalex.org/W2768908787","https://openalex.org/W2780045768","https://openalex.org/W2788316095","https://openalex.org/W2804066752","https://openalex.org/W2804084124","https://openalex.org/W2804911749","https://openalex.org/W2963208223","https://openalex.org/W2963646405","https://openalex.org/W2964263543"],"related_works":["https://openalex.org/W3012292446","https://openalex.org/W6902196909","https://openalex.org/W6995991814","https://openalex.org/W2286466625","https://openalex.org/W2273088453","https://openalex.org/W2470589948","https://openalex.org/W4393157669","https://openalex.org/W3105333898","https://openalex.org/W7127602622","https://openalex.org/W2942437031"],"abstract_inverted_index":{"A":[0],"key":[1],"impediment":[2],"to":[3,44,89,99,120],"reinforcement":[4],"learning":[5],"(RL)":[6],"in":[7,92,108],"real":[8],"applications":[9],"with":[10,69],"limited,":[11],"batch":[12],"data":[13],"is":[14],"defining":[15],"a":[16,29,42,74,109,114,122],"reward":[17,50,100,115],"function":[18],"that":[19,54,82,86,116],"reflects":[20],"what":[21],"we":[22,40,83,87],"implicitly":[23],"know":[24],"about":[25],"reasonable":[26],"behaviour":[27],"for":[28,33,52,113,124],"task":[30],"and":[31,64],"allows":[32],"robust":[34],"off-policy":[35],"evaluation.":[36],"In":[37],"this":[38],"work,":[39],"develop":[41],"method":[43],"identify":[45],"an":[46],"admissible":[47],"set":[48],"of":[49,76],"functions":[51],"policies":[53,85],"(a)":[55],"do":[56],"not":[57],"diverge":[58],"too":[59],"far":[60],"from":[61,127],"past":[62,77],"behaviour,":[63],"(b)":[65],"can":[66],"be":[67,90],"evaluated":[68],"high":[70],"confidence,":[71],"given":[72],"only":[73],"collection":[75],"trajectories.":[78],"Together,":[79],"these":[80],"ensure":[81],"propose":[84],"trust":[88],"implemented":[91],"high-risk":[93],"settings.":[94],"We":[95],"demonstrate":[96],"our":[97],"approach":[98],"design":[101],"on":[102],"synthetic":[103],"domains":[104],"as":[105,107],"well":[106],"critical":[110],"care":[111],"context,":[112],"consolidates":[117],"clinical":[118],"objectives":[119],"learn":[121],"policy":[123],"weaning":[125],"patients":[126],"mechanical":[128],"ventilation.":[129]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2019-06-07T00:00:00"}