{"id":"https://openalex.org/W3012292446","doi":"https://doi.org/10.1145/3368555.3384450","title":"Defining admissible rewards for high-confidence policy evaluation in batch reinforcement learning","display_name":"Defining admissible rewards for high-confidence policy evaluation in batch reinforcement learning","publication_year":2020,"publication_date":"2020-03-20","ids":{"openalex":"https://openalex.org/W3012292446","doi":"https://doi.org/10.1145/3368555.3384450","mag":"3012292446"},"language":"en","primary_location":{"id":"doi:10.1145/3368555.3384450","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3368555.3384450","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3368555.3384450","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on Health, Inference, and Learning","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3368555.3384450","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009328512","display_name":"Niranjani Prasad","orcid":"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":true,"raw_author_name":"Niranjani Prasad","raw_affiliation_strings":["Princeton University, Princeton NJ"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton NJ","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065136437","display_name":"Barbara E. Engelhardt","orcid":"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":"Barbara Engelhardt","raw_affiliation_strings":["Princeton University, Princeton NJ"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton NJ","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"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Finale Doshi-Velez","raw_affiliation_strings":["Harvard SEAS, Cambridge MA"],"affiliations":[{"raw_affiliation_string":"Harvard SEAS, Cambridge MA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009328512"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.02712154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.991100013256073,"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":0.991100013256073,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9567000269889832,"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/T10322","display_name":"Respiratory Support and Mechanisms","score":0.9383999705314636,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8177393078804016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6859934329986572},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6282187700271606},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6150634288787842},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5896824598312378},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.518589973449707},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5116227269172668},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4653644561767578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4370427131652832},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4355568289756775},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.413596510887146},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15313589572906494},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.12618589401245117},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12073624134063721},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07053950428962708}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8177393078804016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6859934329986572},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6282187700271606},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6150634288787842},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5896824598312378},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.518589973449707},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5116227269172668},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4653644561767578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4370427131652832},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4355568289756775},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.413596510887146},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15313589572906494},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.12618589401245117},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12073624134063721},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07053950428962708},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3368555.3384450","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3368555.3384450","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3368555.3384450","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on Health, Inference, and Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3368555.3384450","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3368555.3384450","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3368555.3384450","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on Health, Inference, and Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3012292446.pdf","grobid_xml":"https://content.openalex.org/works/W3012292446.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W88199814","https://openalex.org/W745775011","https://openalex.org/W1514587017","https://openalex.org/W1931027396","https://openalex.org/W1999874108","https://openalex.org/W2069159633","https://openalex.org/W2120346334","https://openalex.org/W2135721773","https://openalex.org/W2135995480","https://openalex.org/W2151161180","https://openalex.org/W2169401877","https://openalex.org/W2273088453","https://openalex.org/W2396881363","https://openalex.org/W2472245206","https://openalex.org/W2535327675","https://openalex.org/W2573422763","https://openalex.org/W2626804490","https://openalex.org/W2750866482","https://openalex.org/W2804066752","https://openalex.org/W2804911749","https://openalex.org/W2896893468","https://openalex.org/W2962676505","https://openalex.org/W2963208223","https://openalex.org/W6677737365"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"A":[0],"key":[1],"impediment":[2],"to":[3,45,98,112,124],"reinforcement":[4],"learning":[5],"(RL)":[6],"in":[7,15,62,91,107],"real":[8],"applications":[9],"with":[10,72],"limited,":[11],"batch":[12],"data":[13],"is":[14],"defining":[16],"a":[17,30,43,77,108,117,126],"reward":[18,51,99,118],"function":[19,119],"that":[20,55,85,120],"reflects":[21],"what":[22],"we":[23,41,86],"implicitly":[24],"know":[25],"about":[26],"reasonable":[27],"behaviour":[28],"for":[29,34,53,128],"task":[31],"and":[32,67],"allows":[33],"robust":[35],"off-policy":[36],"evaluation.":[37],"In":[38],"this":[39],"work,":[40],"develop":[42],"method":[44],"identify":[46],"an":[47],"admissible":[48],"set":[49],"of":[50,79,116],"functions":[52],"policies":[54,90],"(a)":[56],"do":[57],"not":[58],"deviate":[59],"too":[60],"far":[61],"performance":[63],"from":[64,131],"prior":[65],"behaviour,":[66],"(b)":[68],"can":[69],"be":[70],"evaluated":[71],"high":[73],"confidence,":[74],"given":[75],"only":[76],"collection":[78],"past":[80],"trajectories.":[81],"Together,":[82],"these":[83],"ensure":[84],"avoid":[87],"proposing":[88],"unreasonable":[89],"high-risk":[92],"settings.":[93],"We":[94],"demonstrate":[95],"our":[96],"approach":[97],"design":[100,115],"on":[101],"synthetic":[102],"domains":[103],"as":[104,106],"well":[105],"critical":[109],"care":[110],"context,":[111],"guide":[113],"the":[114],"consolidates":[121],"clinical":[122],"objectives":[123],"learn":[125],"policy":[127],"weaning":[129],"patients":[130],"mechanical":[132],"ventilation.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}