{"id":"https://openalex.org/W2923483157","doi":"https://doi.org/10.24963/ijcai.2019/819","title":"Truly Batch Apprenticeship Learning with Deep Successor Features","display_name":"Truly Batch Apprenticeship Learning with Deep Successor Features","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2923483157","doi":"https://doi.org/10.24963/ijcai.2019/819","mag":"2923483157"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/819","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/819","pdf_url":"https://www.ijcai.org/proceedings/2019/0819.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0819.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100348868","display_name":"Donghun Lee","orcid":"https://orcid.org/0000-0002-7941-2395"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]},{"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":true,"raw_author_name":"Donghun Lee","raw_affiliation_strings":["SEAS, Harvard University","Harvard University ,"],"affiliations":[{"raw_affiliation_string":"SEAS, Harvard University","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044157219","display_name":"Srivatsan Srinivasan","orcid":"https://orcid.org/0000-0002-6672-4779"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]},{"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":"Srivatsan Srinivasan","raw_affiliation_strings":["SEAS, Harvard University","Harvard University ,"],"affiliations":[{"raw_affiliation_string":"SEAS, Harvard University","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038771285","display_name":"Finale Doshi\u2010Velez","orcid":"https://orcid.org/0000-0003-2886-3898"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]},{"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":"Finale Doshi-Velez","raw_affiliation_strings":["SEAS, Harvard University","Harvard University ,"],"affiliations":[{"raw_affiliation_string":"SEAS, Harvard University","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100348868"],"corresponding_institution_ids":["https://openalex.org/I136199984","https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":0.76808873,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7716004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5909","last_page":"5915"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9975000023841858,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9975000023841858,"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/T10218","display_name":"Sepsis Diagnosis and Treatment","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9595000147819519,"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/successor-cardinal","display_name":"Successor cardinal","score":0.7896238565444946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7296332120895386},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6132982969284058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.581763505935669},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5481538772583008},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5295280814170837},{"id":"https://openalex.org/keywords/apprenticeship","display_name":"Apprenticeship","score":0.503055989742279},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.4645860493183136},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4550217092037201},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.43223845958709717},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41223156452178955},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3407561480998993},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11771327257156372}],"concepts":[{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.7896238565444946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7296332120895386},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6132982969284058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.581763505935669},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5481538772583008},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5295280814170837},{"id":"https://openalex.org/C107806365","wikidata":"https://www.wikidata.org/wiki/Q253567","display_name":"Apprenticeship","level":2,"score":0.503055989742279},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.4645860493183136},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4550217092037201},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.43223845958709717},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41223156452178955},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3407561480998993},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11771327257156372},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2019/819","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/819","pdf_url":"https://www.ijcai.org/proceedings/2019/0819.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.10077","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.10077","pdf_url":"https://arxiv.org/pdf/1903.10077","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.1903.10077","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.10077","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:2923483157","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/819","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/819","pdf_url":"https://www.ijcai.org/proceedings/2019/0819.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2923483157.pdf","grobid_xml":"https://content.openalex.org/works/W2923483157.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1799240622","https://openalex.org/W1931877416","https://openalex.org/W2098774185","https://openalex.org/W2100401322","https://openalex.org/W2116774898","https://openalex.org/W2123157758","https://openalex.org/W2133068870","https://openalex.org/W2145339207","https://openalex.org/W2148051740","https://openalex.org/W2280404143","https://openalex.org/W2342662072","https://openalex.org/W2347074400","https://openalex.org/W2396161314","https://openalex.org/W2396881363","https://openalex.org/W2554067423","https://openalex.org/W2567252694","https://openalex.org/W2962717849","https://openalex.org/W2962997838","https://openalex.org/W2963277051","https://openalex.org/W2963508354","https://openalex.org/W6650265722","https://openalex.org/W6718092244","https://openalex.org/W6863318804"],"related_works":["https://openalex.org/W3007369745","https://openalex.org/W3102501701","https://openalex.org/W3174070947","https://openalex.org/W3034973310","https://openalex.org/W2999114190","https://openalex.org/W3169840145","https://openalex.org/W3095437761","https://openalex.org/W2103064945","https://openalex.org/W2950600380","https://openalex.org/W3088622234","https://openalex.org/W778742492","https://openalex.org/W2626860042","https://openalex.org/W52170320","https://openalex.org/W2900831917","https://openalex.org/W3084024636","https://openalex.org/W3092600649","https://openalex.org/W2907704766","https://openalex.org/W3043612295","https://openalex.org/W2952136901","https://openalex.org/W3167983015"],"abstract_inverted_index":{"We":[0,77,105],"introduce":[1,107],"a":[2,79,86,91,138],"novel":[3],"apprenticeship":[4],"learning":[5,82,102],"algorithm":[6,41],"to":[7,84,116],"learn":[8,85],"an":[9],"expert's":[10],"underlying":[11],"reward":[12],"structure":[13],"in":[14,56,145],"off-policy":[15,114],"model-free":[16],"batch":[17,44,99,125],"settings.":[18],"Unlike":[19],"existing":[20],"methods":[21],"that":[22,95,112],"require":[23],"hand-crafted":[24],"features,":[25],"on-policy":[26],"evaluation,":[27],"further":[28],"data":[29,45,73],"acquisition":[30,74],"for":[31],"evaluation":[32,115],"policies":[33],"or":[34,62],"the":[35,48,97,124,146],"knowledge":[36],"of":[37,47,120,142],"model":[38,83],"dynamics,":[39],"our":[40,127],"requires":[42],"only":[43],"(demonstrations)":[46],"observed":[49],"expert":[50],"behavior.":[51],"Such":[52],"settings":[53],"are":[54],"common":[55],"many":[57],"real-world":[58],"tasks---health":[59],"care,":[60],"finance,":[61],"industrial":[63],"process":[64,103],"control---where":[65],"accurate":[66],"simulators":[67],"do":[68],"not":[69],"exist":[70],"and":[71,90],"additional":[72],"is":[75],"costly.":[76],"develop":[78],"transition-regularized":[80],"imitation":[81],"rich":[87],"feature":[88,110,118],"representation":[89],"near-expert":[92],"initial":[93],"policy":[94],"makes":[96],"subsequent":[98],"inverse":[100],"reinforcement":[101],"viable.":[104],"also":[106],"deep":[108],"successor":[109],"networks":[111],"perform":[113],"estimate":[117],"expectations":[119],"candidate":[121],"policies.":[122],"Under":[123],"setting,":[126],"method":[128],"achieves":[129],"superior":[130],"results":[131],"on":[132],"control":[133],"benchmarks":[134],"as":[135,137],"well":[136],"real":[139],"clinical":[140],"task":[141],"sepsis":[143],"management":[144],"Intensive":[147],"Care":[148],"Unit.":[149]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}