{"id":"https://openalex.org/W2616305530","doi":"https://doi.org/10.1109/icra.2017.7989680","title":"Probabilistically safe policy transfer","display_name":"Probabilistically safe policy transfer","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2616305530","doi":"https://doi.org/10.1109/icra.2017.7989680","mag":"2616305530"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2017.7989680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1705.05394","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037048516","display_name":"David Held","orcid":"https://orcid.org/0000-0003-0537-1508"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Held","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA 94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA 94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008996507","display_name":"Zoe McCarthy","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zoe McCarthy","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA 94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA 94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100612833","display_name":"Michael Zhang","orcid":"https://orcid.org/0000-0002-4647-3888"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Zhang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA 94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA 94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086456718","display_name":"Fred Shentu","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fred Shentu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA 94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA 94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"id":"https://openalex.org/I4210161460","display_name":"OpenAI (United States)","ror":"https://ror.org/05wx9n238","country_code":"US","type":"company","lineage":["https://openalex.org/I4210161460"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["International Computer Science Institute (ICSI), University of California, Berkeley, CA","OpenAl, San Francisco, CA","Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA 94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute (ICSI), University of California, Berkeley, CA","institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I95457486"]},{"raw_affiliation_string":"OpenAl, San Francisco, CA","institution_ids":["https://openalex.org/I4210161460"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA 94720","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5798","last_page":"5805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9944000244140625,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/limit","display_name":"Limit (mathematics)","score":0.6699078679084778},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6686878204345703},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6611186861991882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6175200343132019},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5981583595275879},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5737829208374023},{"id":"https://openalex.org/keywords/torque","display_name":"Torque","score":0.5613660216331482},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5330919623374939},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5017974376678467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49682310223579407},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4708658754825592},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4642679691314697},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22714439034461975},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1447923183441162},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.088826984167099},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.06750813126564026}],"concepts":[{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.6699078679084778},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6686878204345703},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6611186861991882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6175200343132019},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5981583595275879},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5737829208374023},{"id":"https://openalex.org/C144171764","wikidata":"https://www.wikidata.org/wiki/Q48103","display_name":"Torque","level":2,"score":0.5613660216331482},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5330919623374939},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5017974376678467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49682310223579407},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4708658754825592},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4642679691314697},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22714439034461975},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1447923183441162},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.088826984167099},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.06750813126564026},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra.2017.7989680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1705.05394","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.05394","pdf_url":"https://arxiv.org/pdf/1705.05394","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:2616305530","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1705.05394","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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},{"id":"doi:10.48550/arxiv.1705.05394","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1705.05394","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1705.05394","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.05394","pdf_url":"https://arxiv.org/pdf/1705.05394","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2992220136","display_name":"CAREER: Apprenticeship Learning for Robotic Manipulation of Deformable Objects","funder_award_id":"1351028","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2616305530.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1506085041","https://openalex.org/W1587009522","https://openalex.org/W1967821692","https://openalex.org/W2009812633","https://openalex.org/W2042520683","https://openalex.org/W2079659517","https://openalex.org/W2096615883","https://openalex.org/W2114580749","https://openalex.org/W2125612430","https://openalex.org/W2145339207","https://openalex.org/W2147871016","https://openalex.org/W2158782408","https://openalex.org/W2162849300","https://openalex.org/W2165622730","https://openalex.org/W2198225532","https://openalex.org/W2257979135","https://openalex.org/W2288565641","https://openalex.org/W2342662072","https://openalex.org/W2344023930","https://openalex.org/W2416477367","https://openalex.org/W2418627435","https://openalex.org/W2426267443","https://openalex.org/W2462906003","https://openalex.org/W2949185669","https://openalex.org/W2949248709","https://openalex.org/W2949608212","https://openalex.org/W2952720101","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6680657880","https://openalex.org/W6682367392","https://openalex.org/W6682849425","https://openalex.org/W6687583651","https://openalex.org/W6692846177","https://openalex.org/W6704571135","https://openalex.org/W6718738585","https://openalex.org/W6765793075"],"related_works":["https://openalex.org/W2115482830","https://openalex.org/W2088356556","https://openalex.org/W2126407035","https://openalex.org/W2890408693","https://openalex.org/W2294777805","https://openalex.org/W2983414909","https://openalex.org/W2043896893","https://openalex.org/W2019918358","https://openalex.org/W2231052642","https://openalex.org/W1989167625","https://openalex.org/W3143428789","https://openalex.org/W1583125258","https://openalex.org/W2787041907","https://openalex.org/W3119213448","https://openalex.org/W2000370794","https://openalex.org/W2043743368","https://openalex.org/W2333995904","https://openalex.org/W2065288459","https://openalex.org/W2018945760","https://openalex.org/W1995822984"],"abstract_inverted_index":{"Although":[0],"learning-based":[1],"methods":[2],"have":[3],"great":[4],"potential":[5],"for":[6,67],"robotics,":[7],"one":[8],"concern":[9],"is":[10,87,153],"that":[11,14,83,136,148],"a":[12,38,59,71,106,132],"robot":[13,72,141],"updates":[15],"its":[16,144],"parameters":[17],"might":[18,124],"cause":[19],"large":[20],"amounts":[21],"of":[22,34,70,92,134],"damage":[23,57,85,151],"before":[24],"it":[25],"learns":[26],"the":[27,32,50,55,68,84,93,113,121,126,140,149,157],"optimal":[28],"policy.":[29],"We":[30,63,78,129],"formalize":[31],"idea":[33],"safe":[35],"learning":[36,158],"in":[37],"probabilistic":[39],"sense":[40],"by":[41],"defining":[42],"an":[43],"optimization":[44,66,94],"problem:":[45],"we":[46,104],"desire":[47],"to":[48,81,142],"maximize":[49],"expected":[51,56,150],"return":[52],"while":[53,146],"keeping":[54],"below":[58],"given":[60],"safety":[61],"limit.":[62],"study":[64],"this":[65,102],"case":[69],"manipulator":[73],"with":[74],"safety-based":[75],"torque":[76,114],"limits.":[77],"would":[79],"like":[80],"ensure":[82],"constraint":[86,152],"maintained":[88],"at":[89,98],"every":[90],"step":[91],"and":[95],"not":[96,154],"just":[97],"convergence.":[99],"To":[100],"achieve":[101],"aim,":[103],"introduce":[105],"novel":[107],"method":[108],"which":[109],"predicts":[110],"how":[111,119],"modifying":[112],"limit,":[115],"as":[116,118],"well":[117],"updating":[120],"policy":[122],"parameters,":[123],"affect":[125],"robot's":[127],"safety.":[128],"show":[130],"through":[131],"number":[133],"experiments":[135],"our":[137],"approach":[138],"allows":[139],"improve":[143],"performance":[145],"ensuring":[147],"violated":[155],"during":[156],"process.":[159]},"counts_by_year":[{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}