{"id":"https://openalex.org/W7133300078","doi":"https://doi.org/10.1109/tpami.2026.3669907","title":"On the Equilibrium Between Feasible Zone and Uncertain Model in Safe Exploration","display_name":"On the Equilibrium Between Feasible Zone and Uncertain Model in Safe Exploration","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133300078","doi":"https://doi.org/10.1109/tpami.2026.3669907","pmid":"https://pubmed.ncbi.nlm.nih.gov/41774638"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3669907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3669907","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.00636","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045009897","display_name":"Y. Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujie Yang","raw_affiliation_strings":["School of Vehicle and Mobility and State Key Lab of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7222-0019","affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility and State Key Lab of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I4210145005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128104821","display_name":"Zhilong Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhilong Zheng","raw_affiliation_strings":["School of Vehicle and Mobility and State Key Lab of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-3211-6749","affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility and State Key Lab of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I4210145005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128099802","display_name":"Shengbo Eben Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["School of Vehicle and Mobility and State Key Lab of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4923-3633","affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility and State Key Lab of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I4210145005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210145005"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2506515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"7","first_page":"8344","last_page":"8360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12135","display_name":"Fuzzy Systems and Optimization","score":0.17249999940395355,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12135","display_name":"Fuzzy Systems and Optimization","score":0.17249999940395355,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.05050000175833702,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13371","display_name":"Military Defense Systems Analysis","score":0.04439999908208847,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/constraint","display_name":"Constraint (computer-aided design)","score":0.6187000274658203},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.5299999713897705},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5224999785423279},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5095999836921692},{"id":"https://openalex.org/keywords/feasible-region","display_name":"Feasible region","score":0.4307999908924103},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3756999969482422}],"concepts":[{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6187000274658203},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6093999743461609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5996999740600586},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C177067428","wikidata":"https://www.wikidata.org/wiki/Q17013331","display_name":"Feasible region","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2818000018596649}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2026.3669907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3669907","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41774638","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41774638","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2602.00636","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.00636","pdf_url":"https://arxiv.org/pdf/2602.00636","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.00636","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.00636","pdf_url":"https://arxiv.org/pdf/2602.00636","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.6214715242385864}],"awards":[{"id":"https://openalex.org/G1199464621","display_name":null,"funder_award_id":"L257002","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4592020493","display_name":"Didi Joint Research Center for Future Mobility, Tsinghua University","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133300078.pdf","grobid_xml":"https://content.openalex.org/works/W7133300078.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Ensuring":[0],"the":[1,37,53,62,70,73,77,85,118,133,138,147,153,162,171,187,196],"safety":[2],"of":[3,64,146,173,198],"environmental":[4],"exploration":[5,16,66,122,127,200],"is":[6,36,67,82,159],"a":[7,18,26,93,99,105,113,143,202],"critical":[8],"problem":[9],"in":[10,109],"reinforcement":[11],"learning":[12],"(RL).":[13],"While":[14],"limiting":[15],"to":[17,28,68,98,170],"feasible":[19,39,74,95,135,163,188],"zone":[20,40,75,96,136],"has":[21],"become":[22],"widely":[23],"accepted":[24],"as":[25],"way":[27],"ensure":[29],"safety,":[30],"key":[31],"questions":[32,58],"remain":[33],"unresolved:":[34],"what":[35],"maximum":[38,134],"achievable":[41],"through":[42],"exploration,":[43],"and":[44,76,104,137,167,194],"how":[45],"can":[46],"it":[47],"be":[48],"identified?":[49],"This":[50,80],"paper,":[51],"for":[52],"first":[54,119],"time,":[55],"answers":[56],"these":[57,88],"by":[59,157],"revealing":[60],"that":[61,87,152,182],"goal":[63],"safe":[65,121,125,174,199],"find":[69],"equilibrium":[71,126,172,197],"between":[72,131],"environment":[78,102],"model.":[79,141],"conclusion":[81],"based":[83],"on":[84,177],"understanding":[86],"two":[89],"components":[90],"are":[91],"interdependent:":[92],"larger":[94,114],"leads":[97],"more":[100,106],"accurate":[101,107],"model,":[103,108,149],"turn,":[110],"enables":[111],"exploring":[112],"zone.":[115],"We":[116],"propose":[117],"equilibrium-oriented":[120],"framework":[123],"called":[124],"(SEE),":[128],"which":[129],"alternates":[130],"finding":[132],"least":[139],"uncertain":[140,148,154],"Using":[142],"graph":[144],"formulation":[145],"we":[150],"prove":[151],"model":[155],"obtained":[156],"SEE":[158],"monotonically":[160,165],"refined,":[161],"zones":[164,189],"expand,":[166],"both":[168],"converge":[169],"exploration.":[175],"Experiments":[176],"classic":[178],"control":[179],"tasks":[180],"show":[181],"our":[183],"algorithm":[184],"successfully":[185],"expands":[186],"with":[190],"zero":[191],"constraint":[192],"violation,":[193],"achieves":[195],"within":[201],"few":[203],"iterations.":[204]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-02-07T00:00:00"}