{"id":"https://openalex.org/W3206518985","doi":null,"title":"Safe Model-Based Reinforcement Learning Using Robust Control Barrier Functions.","display_name":"Safe Model-Based Reinforcement Learning Using Robust Control Barrier Functions.","publication_year":2021,"publication_date":"2021-10-11","ids":{"openalex":"https://openalex.org/W3206518985","mag":"3206518985"},"language":"en","primary_location":{"id":"mag:3206518985","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2110.05415","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2110.05415","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030205064","display_name":"Yousef Emam","orcid":"https://orcid.org/0000-0003-0378-5651","observed_orcids":["https://orcid.org/0000-0003-0378-5651"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yousef Emam","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":"https://orcid.org/0000-0003-0378-5651","affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101832839","display_name":"Paul Glotfelter","orcid":"https://orcid.org/0000-0003-3054-8352","observed_orcids":["https://orcid.org/0000-0003-3054-8352"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Glotfelter","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":"https://orcid.org/0000-0003-3054-8352","affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088892134","display_name":"Zsolt Kira","orcid":"https://orcid.org/0000-0002-2626-2004","observed_orcids":["https://orcid.org/0000-0002-2626-2004"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zsolt Kira","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2626-2004","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091125105","display_name":"Magnus Egerstedt","orcid":"https://orcid.org/0000-0003-4213-5299","observed_orcids":["https://orcid.org/0000-0003-4213-5299"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Magnus Egerstedt","raw_affiliation_strings":["University of California, Irvine **"],"raw_orcid":"https://orcid.org/0000-0003-4213-5299","affiliations":[{"raw_affiliation_string":"University of California, Irvine **","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9990000128746033,"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":0.9990000128746033,"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":0.00039999998989515007,"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/T10142","display_name":"Formal Methods in Verification","score":0.00019999999494757503,"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/safe-reinforcement-learning","display_name":"safe reinforcement learning","score":0.8679999709129333},{"id":"https://openalex.org/keywords/control-barrier-functions","display_name":"control barrier functions","score":0.8539999723434448},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.9549999833106995},{"id":"https://openalex.org/keywords/safety-critical-systems","display_name":"safety-critical systems","score":0.9309999942779541},{"id":"https://openalex.org/keywords/exploration-guidance","display_name":"exploration guidance","score":0.7889999747276306},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.8999999761581421}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8494853973388672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840298771858215},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.614208459854126},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48975586891174316},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47147560119628906},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.438579261302948},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4383716881275177},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4260118901729584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3390289545059204},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07983997464179993},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06512236595153809},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3206518985","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2110.05415","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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}],"best_oa_location":{"id":"mag:3206518985","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2110.05415","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1502922572","https://openalex.org/W1518931405","https://openalex.org/W1845972764","https://openalex.org/W1911299338","https://openalex.org/W1977655452","https://openalex.org/W1980569135","https://openalex.org/W1985204762","https://openalex.org/W2027579135","https://openalex.org/W2048723778","https://openalex.org/W2101075098","https://openalex.org/W2560504659","https://openalex.org/W2588802774","https://openalex.org/W2611136914","https://openalex.org/W2618318883","https://openalex.org/W2781726626","https://openalex.org/W2887709062","https://openalex.org/W2899087494","https://openalex.org/W2913300629","https://openalex.org/W2921580065","https://openalex.org/W2925329277","https://openalex.org/W2963082979","https://openalex.org/W2963970238","https://openalex.org/W2964340170","https://openalex.org/W2966735560","https://openalex.org/W2970277495","https://openalex.org/W2970791107","https://openalex.org/W2971353969","https://openalex.org/W2971766219","https://openalex.org/W3100789280","https://openalex.org/W3150718622","https://openalex.org/W4211202104","https://openalex.org/W4292249799"],"related_works":["https://openalex.org/W4312433875","https://openalex.org/W4408319711","https://openalex.org/W3207935216","https://openalex.org/W3154507809","https://openalex.org/W4415237758","https://openalex.org/W2966735560","https://openalex.org/W4417087014","https://openalex.org/W4396242460","https://openalex.org/W4312916991","https://openalex.org/W4317553716"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"is":[3,72],"effective":[4],"in":[5,127,141,160,166],"many":[6],"scenarios.":[7],"However,":[8],"it":[9],"typically":[10],"requires":[11],"the":[12,48,56,79,84,88,118,121,167],"exploration":[13,156],"of":[14,19,23,50,63,90,106,120],"a":[15,35,51,60,67,103,137,142],"sufficiently":[16],"large":[17],"number":[18],"state-action":[20],"pairs,":[21],"some":[22],"which":[24,124],"may":[25],"be":[26],"unsafe.":[27],"Consequently,":[28],"its":[29],"application":[30],"to":[31,44,74,82,115],"safety-critical":[32],"systems":[33],"remains":[34],"challenge.":[36],"Towards":[37],"this":[38,131,148],"end,":[39],"an":[40,111,128],"increasingly":[41],"common":[42],"approach":[43,149],"address":[45],"safety":[46,52,80,122,135,152],"involves":[47],"addition":[49],"layer":[53,81,123,140],"that":[54],"projects":[55],"RL":[57,77,97,144],"actions":[58],"onto":[59],"safe":[61,96],"set":[62],"actions.":[64],"In":[65,87,130],"turn,":[66],"challenge":[68],"for":[69,95,117],"such":[70],"frameworks":[71],"how":[73],"effectively":[75,154],"couple":[76],"with":[78],"improve":[83],"learning":[85],"performance.":[86],"context":[89],"leveraging":[91],"control":[92],"barrier":[93,107],"functions":[94,108],"training,":[98],"prior":[99],"work":[100],"focuses":[101],"on":[102],"restricted":[104],"class":[105],"and":[109,153],"utilizes":[110],"auxiliary":[112],"neural":[113],"net":[114],"account":[116],"effects":[119],"inherently":[125],"results":[126],"approximation.":[129],"paper,":[132],"we":[133],"frame":[134],"as":[136,164],"differentiable":[138],"robust-control-barrier-function":[139],"model-based":[143],"framework.":[145],"As":[146],"such,":[147],"both":[150],"ensures":[151],"guides":[155],"during":[157],"training":[158],"resulting":[159],"increased":[161],"sample":[162],"efficiency":[163],"demonstrated":[165],"experiments.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-10-25T00:00:00"}