{"id":"https://openalex.org/W3207250575","doi":"https://doi.org/10.1109/icra48506.2021.9561593","title":"Context-Aware Safe Reinforcement Learning for Non-Stationary Environments","display_name":"Context-Aware Safe Reinforcement Learning for Non-Stationary Environments","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3207250575","doi":"https://doi.org/10.1109/icra48506.2021.9561593","mag":"3207250575"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5050306497","display_name":"Baiming Chen","orcid":"https://orcid.org/0000-0002-3782-0251"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baiming Chen","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037613999","display_name":"Zuxin Liu","orcid":"https://orcid.org/0000-0001-7412-5074"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zuxin Liu","raw_affiliation_strings":["Department of Mechanical Engineering, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026307285","display_name":"Jiacheng Zhu","orcid":"https://orcid.org/0000-0001-9707-7503"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiacheng Zhu","raw_affiliation_strings":["Department of Mechanical Engineering, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102020639","display_name":"Mengdi Xu","orcid":"https://orcid.org/0000-0001-6087-7558"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengdi Xu","raw_affiliation_strings":["Department of Mechanical Engineering, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058280572","display_name":"Wenhao Ding","orcid":"https://orcid.org/0000-0003-3218-8792"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenhao Ding","raw_affiliation_strings":["Department of Mechanical Engineering, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441194","display_name":"Liang Li","orcid":"https://orcid.org/0000-0002-1577-408X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037644321","display_name":"Ding Zhao","orcid":"https://orcid.org/0000-0002-9400-8446"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ding Zhao","raw_affiliation_strings":["Department of Mechanical Engineering, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10689","last_page":"10695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9919000267982483,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9901000261306763,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8400643467903137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6925634145736694},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6168015003204346},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4727279245853424},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3554058074951172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31446385383605957},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1419891119003296},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.049235641956329346}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8400643467903137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6925634145736694},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6168015003204346},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4727279245853424},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3554058074951172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31446385383605957},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1419891119003296},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.049235641956329346},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9561593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W120291026","https://openalex.org/W1518931405","https://openalex.org/W1845972764","https://openalex.org/W1959608418","https://openalex.org/W2027579135","https://openalex.org/W2257979135","https://openalex.org/W2578206533","https://openalex.org/W2604763608","https://openalex.org/W2605102758","https://openalex.org/W2619551236","https://openalex.org/W2736601468","https://openalex.org/W2784465508","https://openalex.org/W2790355818","https://openalex.org/W2892521964","https://openalex.org/W2904861519","https://openalex.org/W2911087563","https://openalex.org/W2913300629","https://openalex.org/W2949963197","https://openalex.org/W2962974944","https://openalex.org/W2963293747","https://openalex.org/W2963557251","https://openalex.org/W2963864421","https://openalex.org/W2980972480","https://openalex.org/W2994712737","https://openalex.org/W3034840734","https://openalex.org/W3091243689","https://openalex.org/W3105149082","https://openalex.org/W3105252106","https://openalex.org/W3154264273","https://openalex.org/W4288088108","https://openalex.org/W4293545785","https://openalex.org/W4294562617","https://openalex.org/W4298206671","https://openalex.org/W4324105296","https://openalex.org/W6604816053","https://openalex.org/W6640963894","https://openalex.org/W6684763656","https://openalex.org/W6684921986","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6747790125","https://openalex.org/W6751494529","https://openalex.org/W6751535212","https://openalex.org/W6752968661","https://openalex.org/W6756463683","https://openalex.org/W6757223306","https://openalex.org/W6758711939","https://openalex.org/W6758924645","https://openalex.org/W6769246222","https://openalex.org/W6769905080","https://openalex.org/W6771280675","https://openalex.org/W6777387433","https://openalex.org/W6777652781","https://openalex.org/W6779618582","https://openalex.org/W6779812412"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Safety":[0,91],"is":[1,115],"a":[2,60,72],"critical":[3],"concern":[4],"when":[5],"deploying":[6],"reinforcement":[7,15,56],"learning":[8,16,57],"agents":[9],"for":[10],"realistic":[11,118],"tasks.":[12],"Recently,":[13],"safe":[14,55,65],"algorithms":[17],"have":[18,35],"been":[19],"developed":[20],"to":[21,63,77,108],"optimize":[22],"the":[23,37,41,53,82,88,127],"agent\u2019s":[24],"performance":[25],"while":[26],"avoiding":[27],"violations":[28],"of":[29,81,136],"safety":[30,101,110,137],"constraints.":[31],"However,":[32],"few":[33],"studies":[34],"addressed":[36],"nonstationary":[38],"disturbances":[39],"in":[40,67,117,134],"environments,":[42],"which":[43],"may":[44],"cause":[45],"catastrophic":[46],"outcomes.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"context-aware":[54],"(CASRL)":[58],"method,":[59],"metal-earning":[61],"framework":[62],"realize":[64],"adaptation":[66],"non-stationary":[68,122],"environments.":[69],"We":[70],"use":[71],"probabilistic":[73],"latent":[74],"variable":[75],"model":[76],"achieve":[78],"fast":[79],"inference":[80],"posterior":[83],"environment":[84],"transition":[85],"distribution":[86],"given":[87],"context":[89],"data.":[90],"constraints":[92,102],"are":[93,103],"then":[94],"evaluated":[95,116],"with":[96,105,121],"uncertainty-aware":[97],"trajectory":[98],"sampling.":[99],"Prior":[100],"formulated":[104],"domain":[106],"knowledge":[107],"improve":[109],"during":[111],"exploration.":[112],"The":[113],"algorithm":[114,129],"safety-critical":[119],"environments":[120],"disturbances.":[123],"Results":[124],"show":[125],"that":[126],"proposed":[128],"significantly":[130],"outperforms":[131],"existing":[132],"baselines":[133],"terms":[135],"and":[138],"robustness.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}