{"id":"https://openalex.org/W4389880094","doi":"https://doi.org/10.1109/tnnls.2023.3339885","title":"Data-Driven Safe Policy Optimization for Black-Box Dynamical Systems With Temporal Logic Specifications","display_name":"Data-Driven Safe Policy Optimization for Black-Box Dynamical Systems With Temporal Logic Specifications","publication_year":2023,"publication_date":"2023-12-18","ids":{"openalex":"https://openalex.org/W4389880094","doi":"https://doi.org/10.1109/tnnls.2023.3339885","pmid":"https://pubmed.ncbi.nlm.nih.gov/38109255"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3339885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3339885","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5088694458","display_name":"Chenlin Zhang","orcid":"https://orcid.org/0000-0002-5013-7668"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenlin Zhang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100956857","display_name":"Shijun Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijun Lin","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051494127","display_name":"Hao Wang","orcid":"https://orcid.org/0009-0001-3132-2809"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324477","display_name":"Ziyang Chen","orcid":"https://orcid.org/0000-0001-6540-8451"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Chen","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038630321","display_name":"Shaochen Wang","orcid":"https://orcid.org/0000-0002-6985-240X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaochen Wang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018344952","display_name":"Zhen Kan","orcid":"https://orcid.org/0000-0003-2069-9544"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Kan","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5088694458"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3962,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67494086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"36","issue":"2","first_page":"3870","last_page":"3877"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10142","display_name":"Formal Methods in Verification","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.984499990940094,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9779000282287598,"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/black-box","display_name":"Black box","score":0.7324157953262329},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5785714387893677},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.4969015419483185},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23789498209953308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15938881039619446}],"concepts":[{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.7324157953262329},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5785714387893677},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.4969015419483185},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23789498209953308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15938881039619446}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3339885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3339885","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:38109255","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38109255","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 neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1051832680","display_name":null,"funder_award_id":"62173314","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6104967667","display_name":null,"funder_award_id":"U2013601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":42,"referenced_works":["https://openalex.org/W1498432697","https://openalex.org/W2073314543","https://openalex.org/W2089003125","https://openalex.org/W2560504659","https://openalex.org/W2586823359","https://openalex.org/W2771734675","https://openalex.org/W2804791273","https://openalex.org/W2808386811","https://openalex.org/W2966735560","https://openalex.org/W2968945909","https://openalex.org/W2995074243","https://openalex.org/W3006344226","https://openalex.org/W3019114689","https://openalex.org/W3033855706","https://openalex.org/W3039276491","https://openalex.org/W3039715638","https://openalex.org/W3090827750","https://openalex.org/W3094071795","https://openalex.org/W3117756863","https://openalex.org/W3119862069","https://openalex.org/W3120475579","https://openalex.org/W3131411499","https://openalex.org/W3166557699","https://openalex.org/W3182751084","https://openalex.org/W3207935216","https://openalex.org/W4205626291","https://openalex.org/W4206211217","https://openalex.org/W4206742989","https://openalex.org/W4286985629","https://openalex.org/W4317553716","https://openalex.org/W4318983719","https://openalex.org/W6737893269","https://openalex.org/W6746404916","https://openalex.org/W6748839928","https://openalex.org/W6751725685","https://openalex.org/W6771280675","https://openalex.org/W6788898170","https://openalex.org/W6790722625","https://openalex.org/W6793620907","https://openalex.org/W6810667139","https://openalex.org/W6838566501","https://openalex.org/W6840264103"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Learning-based":[0],"policy":[1,25,43,51,146],"optimization":[2,44],"methods":[3,15],"have":[4],"shown":[5],"great":[6],"potential":[7],"for":[8,32,62,74,106,113,147],"building":[9],"general-purpose":[10],"control":[11,58],"systems.":[12,34],"However,":[13],"existing":[14,80],"still":[16],"struggle":[17],"to":[18],"achieve":[19,171],"complex":[20,75,126],"task":[21,76,127,140,179],"objectives":[22],"while":[23],"ensuring":[24],"safety":[26,64,116,174],"during":[27],"learning":[28,49],"and":[29,65,93,142,158,169,176],"execution":[30],"phases":[31],"black-box":[33,107],"To":[35,123],"address":[36],"these":[37],"challenges,":[38],"we":[39,129],"develop":[40,143],"data-driven":[41],"safe":[42,102],"(D2SPO),":[45],"a":[46,57,66,100],"novel":[47],"reinforcement":[48],"(RL)-based":[50],"improvement":[52],"method":[53],"that":[54,82,162],"jointly":[55],"learns":[56],"barrier":[59],"function":[60],"(CBF)":[61],"system":[63,85,115],"linear":[67],"temporal":[68],"logic":[69],"(LTL)":[70],"guided":[71],"RL":[72,118,145],"algorithm":[73],"objectives.":[77,155],"Unlike":[78],"many":[79],"works":[81],"assume":[83],"known":[84],"dynamics,":[86],"by":[87],"carefully":[88],"constructing":[89],"the":[90,95,121,133,139],"data":[91],"sets":[92],"redesigning":[94],"loss":[96],"functions":[97],"of":[98,132,135,150],"D2SPO,":[99],"provably":[101],"CBF":[103],"is":[104,185],"learned":[105],"dynamical":[108],"systems,":[109],"which":[110],"continuously":[111],"evolves":[112],"improved":[114],"as":[117],"interacts":[119],"with":[120,125,153],"environment.":[122],"deal":[124],"objectives,":[128],"take":[130],"advantage":[131],"capability":[134],"LTL":[136,154],"in":[137],"representing":[138],"progress":[141],"LTL-guided":[144],"efficient":[148],"completion":[149,180],"various":[151],"tasks":[152],"Extensive":[156],"numerical":[157],"experimental":[159],"studies":[160],"demonstrate":[161],"D2SPO":[163],"outperforms":[164],"most":[165],"state-of-the-art":[166],"(SOTA)":[167],"baselines":[168],"can":[170],"over":[172],"95%":[173],"rate":[175],"nearly":[177],"100%":[178],"rates.":[181],"The":[182],"experiment":[183],"video":[184],"available":[186],"at":[187],"https://youtu.be/2RgaH-zcmkY.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
