{"id":"https://openalex.org/W3008437631","doi":"https://doi.org/10.1109/jsait.2021.3073257","title":"Empirical Policy Evaluation With Supergraphs","display_name":"Empirical Policy Evaluation With Supergraphs","publication_year":2021,"publication_date":"2021-04-16","ids":{"openalex":"https://openalex.org/W3008437631","doi":"https://doi.org/10.1109/jsait.2021.3073257","mag":"3008437631"},"language":"en","primary_location":{"id":"doi:10.1109/jsait.2021.3073257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsait.2021.3073257","pdf_url":null,"source":{"id":"https://openalex.org/S4210211895","display_name":"IEEE Journal on Selected Areas in Information Theory","issn_l":"2641-8770","issn":["2641-8770"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal on Selected Areas in Information Theory","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.07905","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045537867","display_name":"Daniel Vial","orcid":"https://orcid.org/0000-0003-2426-5604"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Vial","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA","University of Texas at Austin, Austin, TX, USA","University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091601407","display_name":"Vijay Subramanian","orcid":"https://orcid.org/0000-0001-9136-6419"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Subramanian","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA","\u2020University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"\u2020University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045537867"],"corresponding_institution_ids":["https://openalex.org/I27837315","https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00488856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":"2","first_page":"641","last_page":"651"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9962000250816345,"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/T10142","display_name":"Formal Methods in Verification","score":0.9916999936103821,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6849814057350159},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.6830506324768066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6559356451034546},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.6524937748908997},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5739114284515381},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5016968250274658},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.45029306411743164},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3810812532901764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33370059728622437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3265368938446045},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07654309272766113}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6849814057350159},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.6830506324768066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6559356451034546},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6524937748908997},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5739114284515381},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5016968250274658},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.45029306411743164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3810812532901764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33370059728622437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3265368938446045},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07654309272766113},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/jsait.2021.3073257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsait.2021.3073257","pdf_url":null,"source":{"id":"https://openalex.org/S4210211895","display_name":"IEEE Journal on Selected Areas in Information Theory","issn_l":"2641-8770","issn":["2641-8770"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal on Selected Areas in Information Theory","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2002.07905","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.07905","pdf_url":"https://arxiv.org/pdf/2002.07905","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:3008437631","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.07905","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.2002.07905","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.07905","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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.07905","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.07905","pdf_url":"https://arxiv.org/pdf/2002.07905","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"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G274782323","display_name":null,"funder_award_id":"CIF:AF:2008130","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3105902064","display_name":null,"funder_award_id":"EPCN:1603861","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1460549585","https://openalex.org/W1682003616","https://openalex.org/W1762740175","https://openalex.org/W1791063416","https://openalex.org/W1854214752","https://openalex.org/W1989274820","https://openalex.org/W2039191721","https://openalex.org/W2069153192","https://openalex.org/W2086254934","https://openalex.org/W2112264645","https://openalex.org/W2120678009","https://openalex.org/W2181252817","https://openalex.org/W2206616202","https://openalex.org/W2593952959","https://openalex.org/W2743489687","https://openalex.org/W2795158776","https://openalex.org/W2796054047","https://openalex.org/W2943728711","https://openalex.org/W2953330010","https://openalex.org/W2963311874","https://openalex.org/W3030647867","https://openalex.org/W3036981181","https://openalex.org/W3099558206","https://openalex.org/W3121697346","https://openalex.org/W4236323066","https://openalex.org/W4298292701","https://openalex.org/W6630532500","https://openalex.org/W6638415145","https://openalex.org/W6639055396","https://openalex.org/W6741302124","https://openalex.org/W6750007414","https://openalex.org/W6754906582","https://openalex.org/W6992545844"],"related_works":["https://openalex.org/W2962806059","https://openalex.org/W3130958547","https://openalex.org/W2952967722","https://openalex.org/W3178064270","https://openalex.org/W2989321433","https://openalex.org/W2081851784","https://openalex.org/W1859820673","https://openalex.org/W2406454855","https://openalex.org/W3118786471","https://openalex.org/W3040388267","https://openalex.org/W1742716246","https://openalex.org/W2803533594","https://openalex.org/W2914860381","https://openalex.org/W2890489029","https://openalex.org/W2891921153","https://openalex.org/W1589717837","https://openalex.org/W2293715618","https://openalex.org/W35056265","https://openalex.org/W2970699572","https://openalex.org/W2904012376"],"abstract_inverted_index":{"We":[0],"devise":[1],"algorithms":[2,24,63],"for":[3,91],"the":[4,21,49,82],"policy":[5],"evaluation":[6],"problem":[7],"in":[8,34],"reinforcement":[9,92],"learning,":[10],"assuming":[11],"access":[12],"to":[13,30,36,72,86],"a":[14,88],"simulator":[15],"and":[16],"certain":[17],"side":[18],"information":[19],"called":[20],"supergraph.":[22],"Our":[23],"explore":[25],"backward":[26,52],"from":[27,41,69,81],"high-cost":[28],"states":[29],"find":[31],"high-value":[32],"ones,":[33],"contrast":[35],"approaches":[37],"that":[38,61],"work":[39],"forward":[40],"all":[42],"states.":[43],"While":[44],"several":[45],"papers":[46],"have":[47],"demonstrated":[48],"utility":[50],"of":[51],"exploration":[53],"empirically,":[54],"we":[55,78],"conduct":[56],"rigorous":[57],"analyses":[58],"which":[59],"show":[60],"our":[62],"can":[64],"reduce":[65],"average-case":[66],"sample":[67],"complexity":[68],"O(S":[70],"logS)":[71],"as":[73,75],"low":[74],"O(logS).":[76],"Analytically,":[77],"adapt":[79],"tools":[80],"network":[83],"science":[84],"literature":[85],"provide":[87],"new":[89],"methodology":[90],"learning":[93],"problems.":[94]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}