{"id":"https://openalex.org/W4405778803","doi":"https://doi.org/10.1109/iros58592.2024.10801338","title":"Safe Reinforcement Learning via Hierarchical Adaptive Chance-Constraint Safeguards","display_name":"Safe Reinforcement Learning via Hierarchical Adaptive Chance-Constraint Safeguards","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405778803","doi":"https://doi.org/10.1109/iros58592.2024.10801338"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5032213685","display_name":"Zhaorun Chen","orcid":"https://orcid.org/0000-0002-2668-6587"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhaorun Chen","raw_affiliation_strings":["University of Chicago,Department of Computer Science,USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago,Department of Computer Science,USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776767","display_name":"Zhuokai Zhao","orcid":"https://orcid.org/0000-0001-8201-2977"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuokai Zhao","raw_affiliation_strings":["University of Chicago,Department of Computer Science,USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago,Department of Computer Science,USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082052249","display_name":"Tairan He","orcid":null},"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":"Tairan He","raw_affiliation_strings":["Carnegie Mellon University,Robotics Institute,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Robotics Institute,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020357658","display_name":"Binhao Chen","orcid":"https://orcid.org/0000-0003-0275-3746"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binhao Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Mechanical Engineering"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062240654","display_name":"Xuhao Zhao","orcid":"https://orcid.org/0009-0005-7120-4857"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuhao Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Mechanical Engineering"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041133234","display_name":"Liang Gong","orcid":"https://orcid.org/0000-0003-0265-1192"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Gong","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Mechanical Engineering"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100738875","display_name":"Chengliang Liu","orcid":"https://orcid.org/0000-0002-6092-3005"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengliang Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Mechanical Engineering"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5032213685"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29711479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12378","last_page":"12385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.8561999797821045,"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/T10524","display_name":"Traffic control and management","score":0.8561999797821045,"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":0.8460999727249146,"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":0.7958471775054932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6437504291534424},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6193467378616333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5738962292671204},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36951392889022827},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16835281252861023}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7958471775054932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6437504291534424},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6193467378616333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5738962292671204},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36951392889022827},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16835281252861023},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W2051434435","https://openalex.org/W2892521964","https://openalex.org/W2963575966","https://openalex.org/W2966735560","https://openalex.org/W2967727187","https://openalex.org/W3009331570","https://openalex.org/W3011964880","https://openalex.org/W3016333273","https://openalex.org/W3150718622","https://openalex.org/W3156421420","https://openalex.org/W3189576409","https://openalex.org/W3210061731","https://openalex.org/W4206497039","https://openalex.org/W4285813061","https://openalex.org/W4285818823","https://openalex.org/W4315472283","https://openalex.org/W4382317755","https://openalex.org/W4382464024","https://openalex.org/W4385767976","https://openalex.org/W4400874340","https://openalex.org/W6638018090","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6746595151","https://openalex.org/W6747790125","https://openalex.org/W6748512255","https://openalex.org/W6751535212","https://openalex.org/W6751725685","https://openalex.org/W6754113743","https://openalex.org/W6759111761","https://openalex.org/W6779265984","https://openalex.org/W6780032648","https://openalex.org/W6784630725","https://openalex.org/W6784643869","https://openalex.org/W6785187516","https://openalex.org/W6789855942","https://openalex.org/W6790879498","https://openalex.org/W6796910599","https://openalex.org/W6800776581","https://openalex.org/W6803952634","https://openalex.org/W6804601995","https://openalex.org/W6846038489","https://openalex.org/W6856924951"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Ensuring":[0],"safety":[1,68,79,118],"in":[2,23,116,129],"Reinforcement":[3],"Learning":[4],"(RL),":[5],"typically":[6],"framed":[7],"as":[8,32,71],"a":[9,72],"Constrained":[10],"Markov":[11],"Decision":[12],"Process":[13],"(CMDP),":[14],"is":[15],"crucial":[16],"for":[17],"real-world":[18,110,131],"exploration":[19,81],"applications.":[20],"Current":[21],"approaches":[22],"handling":[24],"CMDP":[25],"struggle":[26],"to":[27,76,98],"balance":[28],"optimality":[29,123],"and":[30,41,82,109,126],"feasibility,":[31],"direct":[33],"optimization":[34],"methods":[35,43],"can-not":[36],"ensure":[37,78],"state-wise":[38],"in-training":[39],"safety,":[40],"projection-based":[42],"correct":[44],"actions":[45],"inefficiently":[46],"through":[47],"lengthy":[48],"iterations.":[49],"To":[50],"address":[51],"these":[52],"challenges,":[53],"we":[54],"propose":[55],"Adaptive":[56],"Chance-constrained":[57],"Safeguards":[58],"(ACS),":[59],"an":[60],"adaptive,":[61],"model-free":[62],"safe":[63,100],"RL":[64],"algorithm":[65],"using":[66],"the":[67,90,99],"recovery":[69],"rate":[70],"surrogate":[73],"chance":[74],"constraint":[75,93],"iteratively":[77],"during":[80],"after":[83],"achieving":[84],"convergence.":[85],"Theoretical":[86],"analysis":[87],"indicates":[88],"that":[89],"relaxed":[91],"probabilistic":[92],"sufficiently":[94],"guarantees":[95],"forward":[96],"invariance":[97],"set.":[101],"And":[102],"extensive":[103],"experiments":[104],"conducted":[105],"on":[106],"both":[107],"simulated":[108],"safety-critical":[111],"tasks":[112],"demonstrate":[113],"its":[114],"effectiveness":[115],"enforcing":[117],"(nearly":[119],"zero-violation)":[120],"while":[121],"preserving":[122],"(+23.8%),":[124],"robustness,":[125],"fast":[127],"response":[128],"stochastic":[130],"settings.":[132]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}