{"id":"https://openalex.org/W4401415472","doi":"https://doi.org/10.1109/icra57147.2024.10610856","title":"Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy","display_name":"Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401415472","doi":"https://doi.org/10.1109/icra57147.2024.10610856"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610856","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5104253466","display_name":"Chenyang Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Cao","raw_affiliation_strings":["Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076910727","display_name":"Zichen Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zichen Yan","raw_affiliation_strings":["Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094077105","display_name":"Renhao Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renhao Lu","raw_affiliation_strings":["Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004980453","display_name":"Junbo Tan","orcid":"https://orcid.org/0000-0002-8956-5408"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbo Tan","raw_affiliation_strings":["Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100737124","display_name":"Xueqian Wang","orcid":"https://orcid.org/0000-0003-0013-3930"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqian Wang","raw_affiliation_strings":["Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6109,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73199576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"2838","last_page":"2844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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":0.9973999857902527,"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":0.9699000120162964,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9660999774932861,"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":0.8429833650588989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6864895224571228},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6405164003372192},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3588600158691406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3480178117752075},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15376892685890198},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10005307197570801}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8429833650588989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6864895224571228},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6405164003372192},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3588600158691406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3480178117752075},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15376892685890198},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10005307197570801}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610856","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2962787969","https://openalex.org/W2963575966","https://openalex.org/W2978455699","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3035454705","https://openalex.org/W3098082936","https://openalex.org/W3150718622","https://openalex.org/W3162902207","https://openalex.org/W3172360140","https://openalex.org/W3185083385","https://openalex.org/W3195968524","https://openalex.org/W3207033168","https://openalex.org/W4287113380","https://openalex.org/W4293872189","https://openalex.org/W4300799055","https://openalex.org/W4312347470","https://openalex.org/W4312630992","https://openalex.org/W4321161785","https://openalex.org/W4321392781","https://openalex.org/W4360584316","https://openalex.org/W4367365470","https://openalex.org/W4379256329","https://openalex.org/W6630965284","https://openalex.org/W6687063787","https://openalex.org/W6737893269","https://openalex.org/W6740801417","https://openalex.org/W6745747580","https://openalex.org/W6748599296","https://openalex.org/W6748839928","https://openalex.org/W6751725685","https://openalex.org/W6760822370","https://openalex.org/W6768477783","https://openalex.org/W6776438516","https://openalex.org/W6779265984","https://openalex.org/W6779463497","https://openalex.org/W6780587392","https://openalex.org/W6793841834","https://openalex.org/W6796589144","https://openalex.org/W6802659552","https://openalex.org/W6810117489","https://openalex.org/W6810906561","https://openalex.org/W6840199509","https://openalex.org/W6841115740","https://openalex.org/W6846145766","https://openalex.org/W6846358943","https://openalex.org/W6846881803","https://openalex.org/W6849774883","https://openalex.org/W6850227584","https://openalex.org/W6851539212","https://openalex.org/W6853262171"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Offline":[0],"goal-conditioned":[1],"reinforcement":[2],"learning":[3],"(GCRL)":[4],"aims":[5],"at":[6,62,174],"solving":[7],"goal-reaching":[8],"tasks":[9,92],"with":[10,36,93,110,129],"sparse":[11],"rewards":[12],"from":[13],"an":[14,123],"offline":[15,77,124,131,136],"dataset.":[16,125],"While":[17],"prior":[18],"work":[19],"has":[20],"demonstrated":[21],"various":[22,94],"approaches":[23,49],"for":[24],"agents":[25],"to":[26,89,121,150],"learn":[27],"near-optimal":[28],"policies,":[29],"these":[30,48],"methods":[31,149],"encounter":[32],"limitations":[33],"when":[34],"dealing":[35],"diverse":[37],"constraints":[38],"in":[39],"complex":[40],"environments,":[41],"such":[42],"as":[43],"safety":[44,61],"constraints.":[45],"Some":[46],"of":[47,65,75,161],"prioritize":[50],"goal":[51],"attainment":[52],"without":[53],"considering":[54],"safety,":[55],"while":[56],"others":[57],"excessively":[58],"focus":[59],"on":[60,106,166],"the":[63,73,98,107,146,157],"expense":[64],"training":[66],"efficiency.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,101,155],"study":[72],"problem":[74],"constrained":[76],"GCRL":[78,132],"and":[79,115,134,159],"propose":[80],"a":[81,103,111,141,151,167],"new":[82],"method":[83,99,144],"called":[84],"Recovery-based":[85],"Supervised":[86],"Learning":[87],"(RbSL)":[88],"accomplish":[90],"safety-critical":[91],"goals.":[95],"To":[96],"evaluate":[97],"performance,":[100],"build":[102],"benchmark":[104],"based":[105],"robot-fetching":[108],"environment":[109],"randomly":[112],"positioned":[113],"obstacle":[114],"use":[116],"expert":[117],"or":[118],"random":[119],"policies":[120],"generate":[122],"We":[126],"compare":[127],"RbSL":[128,162],"three":[130],"algorithms":[133],"one":[135],"safe":[137],"RL":[138],"algorithm.":[139],"As":[140],"result,":[142],"our":[143],"outperforms":[145],"existing":[147],"state-of-the-art":[148],"large":[152],"extent.":[153],"Furthermore,":[154],"validate":[156],"practicality":[158],"effectiveness":[160],"by":[163],"deploying":[164],"it":[165],"real":[168],"Panda":[169],"manipulator.":[170],"Code":[171],"is":[172],"available":[173],"https://github.com/Sunlighted/RbSL.git.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}