{"id":"https://openalex.org/W2921596426","doi":"https://doi.org/10.1145/3310090","title":"Probabilistic Policy Reuse for Safe Reinforcement Learning","display_name":"Probabilistic Policy Reuse for Safe Reinforcement Learning","publication_year":2018,"publication_date":"2018-09-30","ids":{"openalex":"https://openalex.org/W2921596426","doi":"https://doi.org/10.1145/3310090","mag":"2921596426"},"language":"en","primary_location":{"id":"doi:10.1145/3310090","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3310090","pdf_url":null,"source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10016/29354","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100645872","display_name":"Javier Garc\u00eda","orcid":"https://orcid.org/0000-0002-5638-5240"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Garc\u00eda","raw_affiliation_strings":["Universidad Carlos III de Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Carlos III de Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004703726","display_name":"Fernando Fern\u00e1ndez","orcid":"https://orcid.org/0000-0003-3801-6801"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Fernando Fern\u00e1ndez","raw_affiliation_strings":["Universidad Carlos III de Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Carlos III de Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I50357001"],"apc_list":null,"apc_paid":null,"fwci":1.3085,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86125284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"13","issue":"3","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9923999905586243,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9873999953269958,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8710644245147705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7984889149665833},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.7351741790771484},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7212432622909546},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5136687159538269},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49903416633605957},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4880620241165161},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4405108690261841},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4138530492782593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3971664011478424},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.39070239663124084},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3782087564468384},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.18498927354812622},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07768753170967102}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8710644245147705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7984889149665833},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.7351741790771484},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7212432622909546},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5136687159538269},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49903416633605957},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4880620241165161},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4405108690261841},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4138530492782593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3971664011478424},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.39070239663124084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3782087564468384},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.18498927354812622},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07768753170967102},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3310090","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3310090","pdf_url":null,"source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"},{"id":"pmh:oai:dnet:earchivo____::a5a8dba5f1c75452021468c4593002ec","is_oa":true,"landing_page_url":"http://hdl.handle.net/10016/29354","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:dnet:earchivo____::a5a8dba5f1c75452021468c4593002ec","is_oa":true,"landing_page_url":"http://hdl.handle.net/10016/29354","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"},{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1867421856","display_name":null,"funder_award_id":"2016-T2/TIC-1712","funder_id":"https://openalex.org/F4320313831","funder_display_name":"Comunidad de Madrid"},{"id":"https://openalex.org/G1982569897","display_name":"EUROPEAN ROBOTIC GOAL-ORIENTED AUTONOMOUS CONTROLLER","funder_award_id":"730086","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4181939816","display_name":null,"funder_award_id":"TIN2015-65686-C5-1-R","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320313831","display_name":"Comunidad de Madrid","ror":null},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W779494576","https://openalex.org/W1515851193","https://openalex.org/W1731081199","https://openalex.org/W1974043469","https://openalex.org/W1983497631","https://openalex.org/W1986014385","https://openalex.org/W1994056022","https://openalex.org/W2012392077","https://openalex.org/W2012587148","https://openalex.org/W2031727428","https://openalex.org/W2036240829","https://openalex.org/W2081348312","https://openalex.org/W2097797606","https://openalex.org/W2101539915","https://openalex.org/W2105486945","https://openalex.org/W2107726111","https://openalex.org/W2125612430","https://openalex.org/W2126385963","https://openalex.org/W2137375617","https://openalex.org/W2151908411","https://openalex.org/W2154549708","https://openalex.org/W2155007355","https://openalex.org/W2532646799","https://openalex.org/W2604738573","https://openalex.org/W2615416403","https://openalex.org/W2619103847","https://openalex.org/W2727037355","https://openalex.org/W2728420778","https://openalex.org/W2735075612","https://openalex.org/W2963428623","https://openalex.org/W3000429007","https://openalex.org/W3005502537","https://openalex.org/W3046126333","https://openalex.org/W3106238320","https://openalex.org/W4205513846","https://openalex.org/W4237913625","https://openalex.org/W6682849425"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W4225269853","https://openalex.org/W3168977894"],"abstract_inverted_index":{"This":[0],"work":[1],"introduces":[2],"Policy":[3,15,97],"Reuse":[4,16,98],"for":[5,20,57],"Safe":[6],"Reinforcement":[7],"Learning":[8],",":[9],"an":[10],"algorithm":[11,47],"that":[12,55,150],"combines":[13],"Probabilistic":[14,96],"and":[17,25,28,41,115,143],"teacher":[18,119],"advice":[19,120],"safe":[21],"exploration":[22,111,132,153],"in":[23,33,66,78,121,138],"dangerous":[24],"continuous":[26],"state":[27,85,89,125],"action":[29],"reinforcement":[30],"learning":[31,94],"problems":[32],"which":[34],"the":[35,42,58,61,88,93,104,110,116,124,130,139,151,161,168,173,179],"dynamic":[36],"behavior":[37],"is":[38,44,76,86,99,134],"reasonably":[39],"smooth":[40],"space":[43,90,126],"Euclidean.":[45],"The":[46],"uses":[48],"a":[49,69,73,84,144],"continuously":[50],"increasing":[51],"monotonic":[52],"risk":[53,74],"function":[54,75],"allows":[56],"identification":[59],"of":[60,80,106,112,118,123,172,178],"probability":[62],"to":[63,101,158,163],"end":[64],"up":[65],"failure":[67],"from":[68,87],"given":[70],"state.":[71],"Such":[72],"defined":[77],"terms":[79,171],"how":[81],"far":[82],"such":[83],"known":[91],"by":[92],"agent.":[95],"used":[100,157],"safely":[102],"balance":[103],"exploitation":[105],"actual":[107],"learned":[108],"knowledge,":[109],"new":[113],"actions,":[114],"request":[117],"parts":[122],"considered":[127],"dangerous.":[128],"Specifically,":[129],"\u03c0-reuse":[131,152],"strategy":[133,154],"used.":[135],"Using":[136],"experiments":[137],"helicopter":[140],"hover":[141],"task":[142],"business":[145],"management":[146],"problem,":[147],"we":[148],"show":[149],"can":[155],"be":[156],"completely":[159],"avoid":[160],"visit":[162],"undesirable":[164],"situations":[165],"while":[166],"maintaining":[167],"performance":[169],"(in":[170],"classical":[174],"long-term":[175],"accumulated":[176],"reward)":[177],"final":[180],"policy":[181],"achieved.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
