{"id":"https://openalex.org/W3009331570","doi":"https://doi.org/10.1109/lra.2020.2976272","title":"Safety Augmented Value Estimation From Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks","display_name":"Safety Augmented Value Estimation From Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks","publication_year":2020,"publication_date":"2020-02-26","ids":{"openalex":"https://openalex.org/W3009331570","doi":"https://doi.org/10.1109/lra.2020.2976272","mag":"3009331570"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2020.2976272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2976272","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055891784","display_name":"Brijen Thananjeyan","orcid":"https://orcid.org/0000-0003-1841-5071"},"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":"Brijen Thananjeyan","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA"],"raw_orcid":"https://orcid.org/0000-0003-1841-5071","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103260170","display_name":"Ashwin Balakrishna","orcid":"https://orcid.org/0000-0002-3508-7850"},"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":"Ashwin Balakrishna","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA"],"raw_orcid":"https://orcid.org/0000-0002-3508-7850","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026281392","display_name":"Ugo Rosolia","orcid":"https://orcid.org/0000-0002-1682-0551"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ugo Rosolia","raw_affiliation_strings":["Department of Mechanical and Civil Engineering, California Institute of Technology, Pasadena, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Civil Engineering, California Institute of Technology, Pasadena, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071898762","display_name":"Felix Li","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":"Felix Li","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016270029","display_name":"Rowan McAllister","orcid":"https://orcid.org/0000-0002-9519-2345"},"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":"Rowan McAllister","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072427753","display_name":"Joseph E. Gonzalez","orcid":"https://orcid.org/0000-0003-2921-956X"},"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":"Joseph E. Gonzalez","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"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":"Sergey Levine","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025067440","display_name":"Francesco Borrelli","orcid":"https://orcid.org/0000-0001-8919-6430"},"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":"Francesco Borrelli","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA"],"raw_orcid":"https://orcid.org/0000-0001-8919-6430","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ken Goldberg","orcid":"https://orcid.org/0000-0001-6747-9499"},"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":"Ken Goldberg","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA"],"raw_orcid":"https://orcid.org/0000-0001-6747-9499","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.6014,"has_fulltext":false,"cited_by_count":90,"citation_normalized_percentile":{"value":0.98526038,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"5","issue":"2","first_page":"3612","last_page":"3619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.9900000095367432,"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"}},"topics":[{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.9900000095367432,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9898999929428101,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9746000170707703,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8513707518577576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6793712973594666},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6302930116653442},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5886062383651733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5773277878761292},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5549767017364502},{"id":"https://openalex.org/keywords/tying","display_name":"Tying","score":0.4835045635700226},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4596424102783203},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.42034003138542175},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3593243956565857},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.22221776843070984},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1473517119884491},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10511001944541931}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8513707518577576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6793712973594666},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6302930116653442},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5886062383651733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5773277878761292},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5549767017364502},{"id":"https://openalex.org/C2780938662","wikidata":"https://www.wikidata.org/wiki/Q973710","display_name":"Tying","level":2,"score":0.4835045635700226},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4596424102783203},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.42034003138542175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3593243956565857},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.22221776843070984},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1473517119884491},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10511001944541931},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2020.2976272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2976272","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:authors.library.caltech.edu:102745","is_oa":false,"landing_page_url":"https://authors.library.caltech.edu/102745/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7999060719","display_name":null,"funder_award_id":"N00014-311","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W2018346149","https://openalex.org/W2041242313","https://openalex.org/W2061417916","https://openalex.org/W2062843008","https://openalex.org/W2117964625","https://openalex.org/W2140135625","https://openalex.org/W2145341417","https://openalex.org/W2151237105","https://openalex.org/W2152536965","https://openalex.org/W2281096776","https://openalex.org/W2462906003","https://openalex.org/W2741122588","https://openalex.org/W2749680651","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2789008106","https://openalex.org/W2887709062","https://openalex.org/W2898917980","https://openalex.org/W2911794543","https://openalex.org/W2953671406","https://openalex.org/W2962803570","https://openalex.org/W2962872206","https://openalex.org/W2962937519","https://openalex.org/W2963099939","https://openalex.org/W2963280855","https://openalex.org/W2963355572","https://openalex.org/W2963376229","https://openalex.org/W2963553847","https://openalex.org/W2963598509","https://openalex.org/W2963683522","https://openalex.org/W2963923407","https://openalex.org/W2963960193","https://openalex.org/W2964990165","https://openalex.org/W3011432977","https://openalex.org/W3031773556","https://openalex.org/W4289125818","https://openalex.org/W4293545785","https://openalex.org/W4293872189","https://openalex.org/W4294555834","https://openalex.org/W4297780563","https://openalex.org/W4298206671","https://openalex.org/W6677611147","https://openalex.org/W6680657880","https://openalex.org/W6681267953","https://openalex.org/W6682367392","https://openalex.org/W6718836005","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6742461812","https://openalex.org/W6747473740","https://openalex.org/W6748599296","https://openalex.org/W6748839928","https://openalex.org/W6751494529","https://openalex.org/W6755864697","https://openalex.org/W6757029329","https://openalex.org/W6761908843","https://openalex.org/W6765596973"],"related_works":["https://openalex.org/W2998037107","https://openalex.org/W1569871744","https://openalex.org/W2379437105","https://openalex.org/W2016024526","https://openalex.org/W3139928442","https://openalex.org/W1567336638","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,42],"(RL)":[2],"for":[3],"robotics":[4],"is":[5,176],"challenging":[6],"due":[7],"to":[8,20,66,128],"the":[9,103,147,155,167],"difficulty":[10],"in":[11,115,139,166],"hand-engineering":[12],"a":[13,38,60,98,131,136,160],"dense":[14],"cost":[15],"function,":[16],"which":[17,26,51],"can":[18],"lead":[19],"unintended":[21],"behavior,":[22],"and":[23,29,59,69,84,95,97,122,173],"dynamical":[24],"uncertainty,":[25],"makes":[27],"exploration":[28,68],"constraint":[30,120],"satisfaction":[31],"challenging.":[32],"We":[33,76],"address":[34],"these":[35],"issues":[36],"with":[37,80],"new":[39],"model-based":[40,83],"reinforcement":[41],"algorithm,":[43],"Safety":[44],"Augmented":[45],"Value":[46],"Estimation":[47],"from":[48],"Demonstrations":[49],"(SAVED),":[50],"uses":[52],"supervision":[53],"that":[54,110],"only":[55],"identifies":[56],"task":[57,101],"completion":[58],"modest":[61],"set":[62],"of":[63,117,154,163],"suboptimal":[64],"demonstrations":[65],"constrain":[67],"learn":[70,130],"efficiently":[71],"while":[72,157],"handling":[73],"complex":[74],"constraints.":[75],"then":[77],"compare":[78],"SAVED":[79,111,158],"3":[81],"state-of-the-art":[82],"model-free":[85],"RL":[86],"algorithms":[87],"on":[88,102,135,146],"6":[89],"standard":[90],"simulation":[91],"benchmarks":[92],"involving":[93],"navigation":[94],"manipulation":[96],"physical":[99],"knot-tying":[100],"da":[104],"Vinci":[105],"surgical":[106],"robot.":[107],"Results":[108],"suggest":[109],"outperforms":[112],"prior":[113],"methods":[114],"terms":[116],"success":[118,161],"rate,":[119],"satisfaction,":[121],"sample":[123],"efficiency,":[124],"making":[125],"it":[126],"feasible":[127],"safely":[129],"control":[132],"policy":[133],"directly":[134],"real":[137],"robot":[138],"less":[140,151],"than":[141,152],"an":[142],"hour.":[143],"For":[144],"tasks":[145],"robot,":[148],"baselines":[149],"succeed":[150],"5%":[153],"time":[156],"has":[159],"rate":[162],"over":[164],"75%":[165],"first":[168],"50":[169],"training":[170],"iterations.":[171],"Code":[172],"supplementary":[174],"material":[175],"available":[177],"at":[178],"https://tinyurl.com/saved-rl.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":31},{"year":2020,"cited_by_count":20}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}