{"id":"https://openalex.org/W3150718622","doi":"https://doi.org/10.1109/lra.2021.3070252","title":"Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones","display_name":"Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones","publication_year":2021,"publication_date":"2021-03-31","ids":{"openalex":"https://openalex.org/W3150718622","doi":"https://doi.org/10.1109/lra.2021.3070252","mag":"3150718622"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3070252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3070252","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":null,"display_name":"Brijen Thananjeyan","orcid":"https://orcid.org/0000-0002-3508-7850"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brijen Thananjeyan","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3508-7850","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ashwin Balakrishna","orcid":"https://orcid.org/0000-0003-1841-5071"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin Balakrishna","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1841-5071","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101603882","display_name":"Suraj Nair","orcid":"https://orcid.org/0000-0002-3999-2436"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suraj Nair","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA, U.S"],"raw_orcid":"https://orcid.org/0000-0002-3999-2436","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA, U.S","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035392658","display_name":"Michael Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Luo","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101973028","display_name":"Krishnan Srinivasan","orcid":"https://orcid.org/0000-0002-0692-1332"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishnan Srinivasan","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0692-1332","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051115770","display_name":"Minho Hwang","orcid":"https://orcid.org/0000-0002-9190-7876"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minho Hwang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9190-7876","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"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/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph E. Gonzalez","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053574266","display_name":"Julian Ibarz","orcid":"https://orcid.org/0000-0002-9920-6978"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian Ibarz","raw_affiliation_strings":["Google AI, Sunnyvale, CA, U.S"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google AI, Sunnyvale, CA, U.S","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chelsea Finn","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA, U.S"],"raw_orcid":"https://orcid.org/0000-0001-6298-0874","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA, U.S","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ken Goldberg","orcid":"https://orcid.org/0000-0001-6747-9499"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ken Goldberg","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6747-9499","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.9863,"has_fulltext":false,"cited_by_count":199,"citation_normalized_percentile":{"value":0.99424674,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"6","issue":"3","first_page":"4915","last_page":"4922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987000226974487,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.7450366020202637},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7277759909629822},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6744694113731384},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.671101450920105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5232436060905457},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.4956763982772827},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.48209884762763977},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.430658221244812},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2932884395122528},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12049993872642517},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08459493517875671},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.07183083891868591}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7450366020202637},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7277759909629822},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6744694113731384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.671101450920105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5232436060905457},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.4956763982772827},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.48209884762763977},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.430658221244812},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2932884395122528},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12049993872642517},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08459493517875671},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07183083891868591},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2021.3070252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3070252","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":null},{"id":"https://openalex.org/F4320316556","display_name":"Amazon Robotics","ror":null},{"id":"https://openalex.org/F4320322923","display_name":"Siemens","ror":"https://ror.org/059mq0909"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W134786152","https://openalex.org/W1518931405","https://openalex.org/W1963790880","https://openalex.org/W2061417916","https://openalex.org/W2101075098","https://openalex.org/W2169206416","https://openalex.org/W2221677593","https://openalex.org/W2293539771","https://openalex.org/W2427917354","https://openalex.org/W2618318883","https://openalex.org/W2734960757","https://openalex.org/W2781726626","https://openalex.org/W2804791273","https://openalex.org/W2810785043","https://openalex.org/W2904246096","https://openalex.org/W2913300629","https://openalex.org/W2962803570","https://openalex.org/W2963484919","https://openalex.org/W2963525569","https://openalex.org/W2963575966","https://openalex.org/W2963683522","https://openalex.org/W2963780574","https://openalex.org/W2963864421","https://openalex.org/W2963958573","https://openalex.org/W2963960193","https://openalex.org/W2964040381","https://openalex.org/W2964222567","https://openalex.org/W2964340170","https://openalex.org/W2968547875","https://openalex.org/W2986399309","https://openalex.org/W3009331570","https://openalex.org/W3011303668","https://openalex.org/W3029839358","https://openalex.org/W3031634197","https://openalex.org/W3091691175","https://openalex.org/W3095135648","https://openalex.org/W3106238320","https://openalex.org/W3167874530","https://openalex.org/W4287629996","https://openalex.org/W4293545785","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W4298206671","https://openalex.org/W6684921986","https://openalex.org/W6696708278","https://openalex.org/W6717915398","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6741515245","https://openalex.org/W6743563064","https://openalex.org/W6746595151","https://openalex.org/W6747473740","https://openalex.org/W6751494529","https://openalex.org/W6751535212","https://openalex.org/W6751725685","https://openalex.org/W6753243525","https://openalex.org/W6757592117","https://openalex.org/W6758924645","https://openalex.org/W6768397756","https://openalex.org/W6770012831","https://openalex.org/W6774899326","https://openalex.org/W6775038317","https://openalex.org/W6784630725"],"related_works":["https://openalex.org/W2930076404","https://openalex.org/W4253519380","https://openalex.org/W2071957557","https://openalex.org/W2596413128","https://openalex.org/W4391249562","https://openalex.org/W2356867392","https://openalex.org/W2782776446","https://openalex.org/W3043170174","https://openalex.org/W2155948905","https://openalex.org/W2357323510"],"abstract_inverted_index":{"Safety":[0],"remains":[1],"a":[2,63,73,112],"central":[3],"obstacle":[4,108],"preventing":[5],"widespread":[6],"use":[7],"of":[8,53],"RL":[9,90,118,123,143,157],"in":[10,17,169,177],"the":[11,69,78,145],"real":[12],"world:":[13],"learning":[14,49],"new":[15],"tasks":[16,99],"uncertain":[18],"environments":[19],"requires":[20,25],"extensive":[21],"exploration,":[22],"but":[23],"safety":[24,81,132],"limiting":[26],"exploration.":[27],"We":[28,87,115],"propose":[29],"Recovery":[30,89,117,142,156],"RL,":[31],"an":[32,101,106],"algorithm":[33],"which":[34,125],"navigates":[35],"this":[36],"tradeoff":[37],"by":[38],"(1)":[39],"leveraging":[40],"offline":[41],"data":[42],"to":[43,80,119],"learn":[44],"about":[45],"constraint":[46,58,83,160],"violating":[47],"zonesbeforepolicy":[48],"and":[50,57,72,100,105,131,139,162,172,182],"(2)separatingthe":[51],"goals":[52],"improving":[54],"task":[55,64,70,110,129,163],"performance":[56,130],"satisfaction":[59],"across":[60,150],"two":[61,96],"policies:":[62],"policy":[65,75],"that":[66,76,141,155],"only":[67],"optimizes":[68],"reward":[71,137],"recovery":[74],"guides":[77],"agent":[79],"when":[82],"violation":[84],"is":[85],"likely.":[86],"evaluate":[88],"on":[91,111],"6":[92],"simulation":[93,170],"domains,":[94],"including":[95],"contact-rich":[97],"manipulation":[98],"image-based":[102,107],"navigation":[103],"task,":[104],"avoidance":[109],"physical":[113,178],"robot.":[114],"compare":[116],"5":[120],"prior":[121,148],"safe":[122],"methods":[124],"jointly":[126],"optimize":[127],"for":[128],"via":[133],"constrained":[134],"optimization":[135],"or":[136],"shaping":[138],"find":[140],"outperforms":[144],"next":[146],"best":[147],"method":[149],"all":[151],"domains.":[152],"Results":[153],"suggest":[154],"trades":[158],"off":[159],"violations":[161],"successes":[164],"2\u201320":[165],"times":[166,174],"more":[167,175],"efficiently":[168,176],"domains":[171],"3":[173],"experiments.":[179],"Seehttps://tinyurl.com/rl-recoveryfor":[180],"videos":[181],"supplementary":[183],"material.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":42},{"year":2023,"cited_by_count":45},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}