{"id":"https://openalex.org/W2591506851","doi":"https://doi.org/10.24963/ijcai.2017/237","title":"Sample Efficient Policy Search for Optimal Stopping Domains","display_name":"Sample Efficient Policy Search for Optimal Stopping Domains","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2591506851","doi":"https://doi.org/10.24963/ijcai.2017/237","mag":"2591506851"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/237","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/237","pdf_url":"https://www.ijcai.org/proceedings/2017/0237.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth 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/2017/0237.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063897942","display_name":"Karan Goel","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Karan Goel","raw_affiliation_strings":["Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015966835","display_name":"Christoph Dann","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christoph Dann","raw_affiliation_strings":["Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084989076","display_name":"Emma Brunskill","orcid":"https://orcid.org/0000-0002-3971-7127"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emma Brunskill","raw_affiliation_strings":["Stanford University","Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063897942"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01591924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1711","last_page":"1717"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9991000294685364,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9991000294685364,"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":0.9980999827384949,"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/T12288","display_name":"Optimization and Search Problems","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/logarithm","display_name":"Logarithm","score":0.7336195707321167},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.661559522151947},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6441892385482788},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6401357650756836},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.6301756501197815},{"id":"https://openalex.org/keywords/optimal-stopping","display_name":"Optimal stopping","score":0.6006393432617188},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5845423936843872},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5130218863487244},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.47213417291641235},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.46636542677879333},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4528026878833771},{"id":"https://openalex.org/keywords/stopping-time","display_name":"Stopping time","score":0.4447689652442932},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.442293256521225},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.42248696088790894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23496109247207642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14872679114341736},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11782389879226685},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11770421266555786},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07537731528282166}],"concepts":[{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.7336195707321167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.661559522151947},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6441892385482788},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6401357650756836},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.6301756501197815},{"id":"https://openalex.org/C99414536","wikidata":"https://www.wikidata.org/wiki/Q7098950","display_name":"Optimal stopping","level":2,"score":0.6006393432617188},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5845423936843872},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5130218863487244},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.47213417291641235},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.46636542677879333},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4528026878833771},{"id":"https://openalex.org/C99888217","wikidata":"https://www.wikidata.org/wiki/Q1288707","display_name":"Stopping time","level":2,"score":0.4447689652442932},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.442293256521225},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.42248696088790894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23496109247207642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14872679114341736},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11782389879226685},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11770421266555786},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07537731528282166},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2017/237","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/237","pdf_url":"https://www.ijcai.org/proceedings/2017/0237.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1702.06238","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1702.06238","pdf_url":"https://arxiv.org/pdf/1702.06238","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":"mag:2591506851","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1702.06238","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1702.06238","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1702.06238","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"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/237","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/237","pdf_url":"https://www.ijcai.org/proceedings/2017/0237.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7492258026","display_name":"BIGDATA: F: BCC: Data driven optimization of classroom learning activities","funder_award_id":"1546510","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2591506851.pdf","grobid_xml":"https://content.openalex.org/works/W2591506851.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1543966358","https://openalex.org/W1601974704","https://openalex.org/W1915939971","https://openalex.org/W2010718550","https://openalex.org/W2015040676","https://openalex.org/W2026621533","https://openalex.org/W2051220593","https://openalex.org/W2059183841","https://openalex.org/W2110423105","https://openalex.org/W2121103318","https://openalex.org/W2139015071","https://openalex.org/W2145957964","https://openalex.org/W2148032167","https://openalex.org/W2151078973","https://openalex.org/W2155027007","https://openalex.org/W2156168464","https://openalex.org/W2161521419","https://openalex.org/W2162412417","https://openalex.org/W2293642138"],"related_works":["https://openalex.org/W2951886426","https://openalex.org/W2963057120","https://openalex.org/W2470589948","https://openalex.org/W2902668302","https://openalex.org/W2948104910","https://openalex.org/W2765274790","https://openalex.org/W2951962403","https://openalex.org/W3092750504","https://openalex.org/W2945934495","https://openalex.org/W2479049856","https://openalex.org/W2408280519","https://openalex.org/W122154553","https://openalex.org/W2970689413","https://openalex.org/W2188902571","https://openalex.org/W2909648661","https://openalex.org/W2244083851","https://openalex.org/W2128281152","https://openalex.org/W3133767525","https://openalex.org/W2197146024","https://openalex.org/W2756036450"],"abstract_inverted_index":{"Optimal":[0],"stopping":[1],"problems":[2],"consider":[3],"the":[4,22,38,63,94],"question":[5],"of":[6,24,66,73,96],"deciding":[7],"when":[8,32],"to":[9,16,69,81],"stop":[10],"an":[11],"observation-generating":[12],"process":[13],"in":[14,29],"order":[15],"maximize":[17],"a":[18,43],"return.":[19],"We":[20,40,61,91],"examine":[21,93],"problem":[23,59],"simultaneously":[25],"learning":[26],"and":[27,45,102],"planning":[28],"such":[30],"domains,":[31],"data":[33,53],"is":[34],"collected":[35],"directly":[36],"from":[37,109],"environment.":[39],"propose":[41],"GFSE,":[42],"simple":[44],"flexible":[46],"model-free":[47,103],"policy":[48,74],"search":[49],"method":[50,98],"that":[51],"reuses":[52],"for":[54,88],"sample":[55,64],"efficiency":[56],"by":[57],"leveraging":[58],"structure.":[60],"bound":[62],"complexity":[65],"our":[67,89,97],"approach":[68],"guarantee":[70],"uniform":[71],"convergence":[72],"value":[75],"estimates,":[76],"tightening":[77],"existing":[78],"PAC":[79],"bounds":[80],"achieve":[82],"logarithmic":[83],"dependence":[84],"on":[85,105],"horizon":[86],"length":[87],"setting.":[90],"also":[92],"benefit":[95],"against":[99],"prevalent":[100],"model-based":[101],"approaches":[104],"3":[106],"domains":[107],"taken":[108],"diverse":[110],"fields.":[111]},"counts_by_year":[],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}