{"id":"https://openalex.org/W2253157232","doi":null,"title":"Direct Policy Iteration with Demonstrations","display_name":"Direct Policy Iteration with Demonstrations","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W2253157232","mag":"2253157232"},"language":"en","primary_location":{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/25288","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/25288","pdf_url":"http://hdl.handle.net/20.500.12210/25288","source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'\u00c9tudes en Civilisations, Langues et Lettres \u00c9trang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"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":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.12210/25288","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006643533","display_name":"Jessica J. Chemali","orcid":null,"observed_orcids":[]},"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":"Chemali, Jessica","raw_affiliation_strings":["Computer Science Department - Carnegie Mellon University (Computer Science Department Carnegie Mellon University Pittsburgh, PA - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department - Carnegie Mellon University (Computer Science Department Carnegie Mellon University Pittsburgh, PA - United States)","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014791481","display_name":"Alessandro Lazaric","orcid":"https://orcid.org/0000-0002-8970-413X","observed_orcids":["https://orcid.org/0000-0002-8970-413X"]},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I4387153239","display_name":"Centre de Recherche en Informatique, Signal et Automatique de Lille","ror":"https://ror.org/05vrs3189","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lazaric, Alessandro","raw_affiliation_strings":["CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (Universit\u00e9 de Lille - Campus scientifique - B\u00e2timent ESPRIT - Avenue Henri Poincar\u00e9 - 59655 Villeneuve d\u2019Ascq - France)","SEQUEL - Sequential Learning (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (Universit\u00e9 de Lille - Campus scientifique - B\u00e2timent ESPRIT - Avenue Henri Poincar\u00e9 - 59655 Villeneuve d\u2019Ascq - France)","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I4387153239"]},{"raw_affiliation_string":"SEQUEL - Sequential Learning (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0741,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.79536136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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":0.001500000013038516,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/expert-demonstrations","display_name":"expert demonstrations","score":0.9440000057220459},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9120000004768372},{"id":"https://openalex.org/keywords/reinforcement-learning-from-demonstration","display_name":"reinforcement learning from demonstration","score":0.5979999899864197},{"id":"https://openalex.org/keywords/optimal-policy-learning","display_name":"optimal policy learning","score":0.5320000052452087},{"id":"https://openalex.org/keywords/theoretical-performance-analysis","display_name":"theoretical performance analysis","score":0.5669999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7985432147979736},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7673354148864746},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6046743392944336},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5551530718803406},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4578472673892975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4252345860004425},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4243854284286499},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3380086421966553},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33800286054611206},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33452531695365906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32211458683013916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1100773811340332},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/25288","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/25288","pdf_url":"http://hdl.handle.net/20.500.12210/25288","source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'\u00c9tudes en Civilisations, Langues et Lettres \u00c9trang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"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":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-01237659v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01237659","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"IJCAI - 24th International Joint Conference on Artificial Intelligence, Jul 2015, Buenos Aires, Argentina","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/25288","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/25288","pdf_url":"http://hdl.handle.net/20.500.12210/25288","source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'\u00c9tudes en Civilisations, Langues et Lettres \u00c9trang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"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":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1729111207","display_name":"Extraction and Transfer of Knowledge in Reinforcement Learning","funder_award_id":"ANR-14-CE24-0010","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320322727","display_name":"Minist\u00e8re de l'Education Nationale, de l'Enseignement Superieur et de la Recherche","ror":"https://ror.org/03sjk9a61"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2253157232.pdf","grobid_xml":"https://content.openalex.org/works/W2253157232.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W106792269","https://openalex.org/W112666333","https://openalex.org/W1575592356","https://openalex.org/W1576452626","https://openalex.org/W1730555343","https://openalex.org/W1931877416","https://openalex.org/W1994123361","https://openalex.org/W1999874108","https://openalex.org/W2061562262","https://openalex.org/W2094387729","https://openalex.org/W2119678437","https://openalex.org/W2133552775","https://openalex.org/W2134289401","https://openalex.org/W2142641780","https://openalex.org/W2153635508","https://openalex.org/W2158738729","https://openalex.org/W2165060096"],"related_works":["https://openalex.org/W7036081215","https://openalex.org/W4390437693","https://openalex.org/W7100301612","https://openalex.org/W3139021136","https://openalex.org/W2133552775","https://openalex.org/W1521625446","https://openalex.org/W4414886937","https://openalex.org/W7098683084","https://openalex.org/W6922521984","https://openalex.org/W2103235543"],"abstract_inverted_index":{"We":[0,25],"consider":[1],"the":[2,6,54,66,74,84,90],"problem":[3],"of":[4,9,36,51,65,83],"learning":[5],"optimal":[7],"policy":[8,29],"an":[10,43,80],"unknown":[11],"Markov":[12],"decision":[13],"process":[14],"(MDP)":[15],"when":[16],"expert":[17,39],"demonstrations":[18],"are":[19],"available":[20],"along":[21],"with":[22,89],"interaction":[23,37],"samples.":[24],"build":[26],"on":[27,72],"classification-based":[28],"iteration":[30],"to":[31],"perform":[32],"a":[33,61,87],"seamless":[34],"integration":[35],"and":[38,86],"data,":[40],"thus":[41],"obtaining":[42],"algorithm":[44,75,85],"which":[45],"can":[46],"benefit":[47],"from":[48],"both":[49],"sources":[50],"information":[52],"at":[53],"same":[55],"time.":[56],"Furthermore":[57],",":[58],"we":[59,78],"provide":[60],"full":[62],"theoretical":[63],"analysis":[64],"performance":[67],"across":[68],"iterations":[69],"providing":[70],"insights":[71],"how":[73],"works.":[76],"Finally,":[77],"report":[79],"empirical":[81],"evaluation":[82],"comparison":[88],"state-of-the-art":[91],"algorithms.":[92]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}
