{"id":"https://openalex.org/W1995959609","doi":"https://doi.org/10.1109/adprl.2011.5967364","title":"Active exploration by searching for experiments that falsify the computed control policy","display_name":"Active exploration by searching for experiments that falsify the computed control policy","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W1995959609","doi":"https://doi.org/10.1109/adprl.2011.5967364","mag":"1995959609"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2011.5967364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbi.uliege.be/handle/2268/88934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031489638","display_name":"Rapha\u00ebl Fonteneau","orcid":"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","Dept. of Electrical Engineering and Computer Science; University of Liege; 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"]},{"raw_affiliation_string":"Dept. of Electrical Engineering and Computer Science; University of Liege; 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"},"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 A. Murphy","raw_affiliation_strings":["Department of Statistics, University of Michigan, USA","Department of Statistics , University of Michigan , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Statistics , University of Michigan , USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047749689","display_name":"Louis Wehenkel","orcid":"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","Dept. of Electrical Engineering and Computer Science; University of Liege; 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"]},{"raw_affiliation_string":"Dept. of Electrical Engineering and Computer Science; University of Liege; 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"},"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","Dept. of Electrical Engineering and Computer Science; University of Liege; 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"]},{"raw_affiliation_string":"Dept. of Electrical Engineering and Computer Science; University of Liege; 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":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"307","issue":null,"first_page":"40","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9937000274658203,"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":0.9937000274658203,"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":0.9912999868392944,"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/T11182","display_name":"Auction Theory and Applications","score":0.9739000201225281,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.841507077217102},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.7548325657844543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7327388525009155},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7069233655929565},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6057243347167969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5769365429878235},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5301236510276794},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5144948959350586},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5080292224884033},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4682890772819519},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.442920982837677},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.43144991993904114},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42416948080062866},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2687985599040985},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13970935344696045}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.841507077217102},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.7548325657844543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7327388525009155},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7069233655929565},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6057243347167969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5769365429878235},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5301236510276794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5144948959350586},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5080292224884033},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4682890772819519},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.442920982837677},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.43144991993904114},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42416948080062866},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2687985599040985},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13970935344696045},{"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/adprl.2011.5967364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:orbi.ulg.ac.be:2268/88934","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/88934","pdf_url":null,"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,"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 2011 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-11) (2011-04); 2011 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-11), Paris, France [FR], April 11-15, 2011","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":{"id":"pmh:oai:orbi.ulg.ac.be:2268/88934","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/88934","pdf_url":null,"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,"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 2011 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-11) (2011-04); 2011 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-11), Paris, France [FR], April 11-15, 2011","raw_type":"http://purl.org/coar/resource_type/c_5794"},"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7057898911","display_name":null,"funder_award_id":"P50 DA10075","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7087725770","display_name":null,"funder_award_id":"R01 MH080015","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320321390","display_name":"Fonds De La Recherche Scientifique - FNRS","ror":"https://ror.org/03q83t159"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334840","display_name":"Fonds pour la Formation \u00e0 la Recherche dans l\u2019Industrie et dans l\u2019Agriculture","ror":"https://ror.org/03q83t159"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W65193931","https://openalex.org/W166862392","https://openalex.org/W1503631637","https://openalex.org/W1550698229","https://openalex.org/W1552830313","https://openalex.org/W1626155273","https://openalex.org/W1931792391","https://openalex.org/W1967005434","https://openalex.org/W1973458764","https://openalex.org/W2027795129","https://openalex.org/W2096258902","https://openalex.org/W2103581319","https://openalex.org/W2108114251","https://openalex.org/W2120346334","https://openalex.org/W2134243390","https://openalex.org/W2165612525","https://openalex.org/W2240994301","https://openalex.org/W2257991595","https://openalex.org/W2266890668","https://openalex.org/W2268509491","https://openalex.org/W2270311916","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W4245296547","https://openalex.org/W4301630257","https://openalex.org/W6602690695","https://openalex.org/W6606719070","https://openalex.org/W6675735773","https://openalex.org/W6676576766","https://openalex.org/W6677737365","https://openalex.org/W6690124040","https://openalex.org/W6692285282","https://openalex.org/W6693974688","https://openalex.org/W6694493349"],"related_works":["https://openalex.org/W4388311650","https://openalex.org/W4362501864","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W1965695708","https://openalex.org/W2120009678","https://openalex.org/W2912947802","https://openalex.org/W2037601570","https://openalex.org/W2123856982","https://openalex.org/W1530089576"],"abstract_inverted_index":{"We":[0,47],"propose":[1],"a":[2,52,55,60,66,82,96],"strategy":[3],"for":[4,95],"experiment":[5],"selection":[6],"-":[7,14],"in":[8,51],"the":[9,17,20,34,39,43,73,85,106],"context":[10,53],"of":[11,84],"reinforcement":[12],"learning":[13,57],"based":[15],"on":[16],"idea":[18,50],"that":[19,32,105],"most":[21,35],"interesting":[22],"experiments":[23],"to":[24,37,80],"carry":[25],"out":[26],"at":[27],"some":[28],"stage":[29],"are":[30,33,64,69,78,93],"those":[31],"liable":[36],"falsify":[38],"current":[40],"hypothesis":[41],"about":[42],"optimal":[44],"control":[45,87],"policy.":[46,88],"cast":[48],"this":[49],"where":[54],"policy":[56],"algorithm":[58],"and":[59,90],"model":[61],"identification":[62],"method":[63],"given":[65],"priori.":[67],"Experiments":[68],"selected":[70],"if,":[71],"using":[72],"learnt":[74,86],"environment":[75],"model,":[76],"they":[77],"predicted":[79],"yield":[81],"revision":[83],"Algorithms":[89],"simulation":[91],"results":[92],"provided":[94],"deterministic":[97],"system":[98],"with":[99],"discrete":[100],"action":[101],"space.":[102],"They":[103],"show":[104],"proposed":[107],"approach":[108],"is":[109],"promising.":[110]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}