{"id":"https://openalex.org/W2158013963","doi":"https://doi.org/10.1109/adprl.2009.4927534","title":"Inferring bounds on the performance of a control policy from a sample of trajectories","display_name":"Inferring bounds on the performance of a control policy from a sample of trajectories","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W2158013963","doi":"https://doi.org/10.1109/adprl.2009.4927534","mag":"2158013963"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2009.4927534","doi":"https://doi.org/10.1109/adprl.2009.4927534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927534","pdf_url":null,"source":{"id":"https://openalex.org/S4306422848","display_name":"IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbi.uliege.be/bitstream/2268/13667/1/bounds-trajectories-adprl.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031489638","display_name":"Raphael Fonteneau D","orcid":"https://orcid.org/0000-0002-7850-1548","observed_orcids":["https://orcid.org/0000-0002-7850-1548"]},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Raphael Fonteneau","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Li\u00e8ge, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070589969","display_name":"Susan A. Murphy","orcid":"https://orcid.org/0000-0002-2032-4286","observed_orcids":["https://orcid.org/0000-0002-2032-4286"]},"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":"Susan Murphy","raw_affiliation_strings":["University of Michigan, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047749689","display_name":"Louis A. Wehenkel","orcid":"https://orcid.org/0000-0001-6649-2405","observed_orcids":["https://orcid.org/0000-0001-6649-2405"]},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Louis Wehenkel","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Li\u00e8ge, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077011518","display_name":"Damien Ernst","orcid":"https://orcid.org/0000-0002-3035-8260","observed_orcids":["https://orcid.org/0000-0002-3035-8260","https://orcid.org/0009-0002-3037-8883","https://orcid.org/0009-0007-7001-0713"]},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Damien Ernst","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Li\u00e8ge, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8155,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92162912,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"3","issue":null,"first_page":"117","last_page":"123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9291999936103821,"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":0.9291999936103821,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.05829999968409538,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.0031999999191612005,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/deterministic-dynamics","display_name":"deterministic dynamics","score":0.6380000114440918},{"id":"https://openalex.org/keywords/polynomial-time-algorithms","display_name":"polynomial-time algorithms","score":0.6460000276565552},{"id":"https://openalex.org/keywords/sample-density","display_name":"sample density","score":0.7049999833106995},{"id":"https://openalex.org/keywords/policy-evaluation","display_name":"policy evaluation","score":0.3919999897480011},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.4659999907016754}],"concepts":[{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.785384476184845},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.7040834426879883},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.6164368987083435},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5314786434173584},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.5309046506881714},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5003111362457275},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.48317447304725647},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.46087318658828735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45975446701049805},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.45827579498291016},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45434993505477905},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43357905745506287},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40406370162963867},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.39839640259742737},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3214321434497833},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18648988008499146},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.133874773979187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11916419863700867},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08516597747802734},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06250190734863281},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/adprl.2009.4927534","doi":"https://doi.org/10.1109/adprl.2009.4927534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927534","pdf_url":null,"source":{"id":"https://openalex.org/S4306422848","display_name":"IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:orbi.ulg.ac.be:2268/13667","doi":null,"is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/13667","pdf_url":"https://orbi.uliege.be/bitstream/2268/13667/1/bounds-trajectories-adprl.pdf","source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-09), 117-123 (2009); IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-09), Nashville, United States [US], March 30 - April 2, 2009","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":{"id":"pmh:oai:orbi.ulg.ac.be:2268/13667","doi":null,"is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/13667","pdf_url":"https://orbi.uliege.be/bitstream/2268/13667/1/bounds-trajectories-adprl.pdf","source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-09), 117-123 (2009); IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-09), Nashville, United States [US], March 30 - April 2, 2009","raw_type":"http://purl.org/coar/resource_type/c_5794"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321390","display_name":"Fonds De La Recherche Scientifique - FNRS","ror":"https://ror.org/03q83t159"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2158013963.pdf","grobid_xml":"https://content.openalex.org/works/W2158013963.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W292508636","https://openalex.org/W1550698229","https://openalex.org/W1576452626","https://openalex.org/W1973458764","https://openalex.org/W1976578332","https://openalex.org/W1991133427","https://openalex.org/W2027795129","https://openalex.org/W2098432798","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2122701159","https://openalex.org/W2165612525","https://openalex.org/W2257991595","https://openalex.org/W3102923851","https://openalex.org/W4214717370","https://openalex.org/W4242606736","https://openalex.org/W4245296547","https://openalex.org/W4285719527","https://openalex.org/W4307347247"],"related_works":["https://openalex.org/W1936364850","https://openalex.org/W319378018","https://openalex.org/W2270311916","https://openalex.org/W7214043379","https://openalex.org/W2284456400","https://openalex.org/W3142346506","https://openalex.org/W4294566399","https://openalex.org/W2963208223","https://openalex.org/W7018161522","https://openalex.org/W1990169017"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2,16],"approach":[3],"for":[4],"inferring":[5],"bounds":[6],"on":[7],"the":[8,31,55,61,78],"finite-horizon":[9],"return":[10],"of":[11,19,54,60,77],"a":[12,49],"control":[13,26,33],"policy":[14],"from":[15],"off-policy":[17],"sample":[18,56,79],"trajectories":[20],"collecting":[21],"state":[22],"transitions,":[23],"rewards,":[24],"and":[25,35,43,58,70],"actions.":[27],"In":[28],"this":[29],"paper,":[30],"dynamics,":[32],"policy,":[34],"reward":[36],"function":[37],"are":[38],"supposed":[39],"to":[40,66],"be":[41],"deterministic":[42],"Lipschitz":[44],"continuous.":[45],"Under":[46],"these":[47,68],"assumptions,":[48],"polynomial":[50],"algorithm,":[51],"in":[52,75],"terms":[53,76],"size":[57],"length":[59],"optimization":[62],"horizon,":[63],"is":[64,73],"derived":[65],"compute":[67],"bounds,":[69],"their":[71],"tightness":[72],"characterized":[74],"density.":[80]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}