{"id":"https://openalex.org/W3197314723","doi":"https://doi.org/10.1109/cdc45484.2021.9683009","title":"Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach","display_name":"Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W3197314723","doi":"https://doi.org/10.1109/cdc45484.2021.9683009","mag":"3197314723"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9683009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683009","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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/A5103171121","display_name":"Xiaowu Sun","orcid":"https://orcid.org/0000-0002-9216-0866"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaowu Sun","raw_affiliation_strings":["University of California,Department of Electrical Engineering and Computer Science,Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical Engineering and Computer Science,Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009564863","display_name":"Wael Fatnassi","orcid":"https://orcid.org/0000-0002-4600-0909"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wael Fatnassi","raw_affiliation_strings":["University of California,Department of Electrical Engineering and Computer Science,Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical Engineering and Computer Science,Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074348678","display_name":"Ulices Santa Cruz","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ulices Santa Cruz","raw_affiliation_strings":["University of California,Department of Electrical Engineering and Computer Science,Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical Engineering and Computer Science,Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019844918","display_name":"Yasser Shoukry","orcid":"https://orcid.org/0000-0002-8224-8477"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasser Shoukry","raw_affiliation_strings":["University of California,Department of Electrical Engineering and Computer Science,Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical Engineering and Computer Science,Irvine","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":0.5861,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68512636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2963","last_page":"2968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T10876","display_name":"Fault Detection and Control Systems","score":0.9976000189781189,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.995199978351593,"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":0.8285393714904785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8070540428161621},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7408882975578308},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7380691766738892},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.609312117099762},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5926617383956909},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5714809894561768},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5568724274635315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5110749006271362},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.46098455786705017},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44655197858810425},{"id":"https://openalex.org/keywords/dynamical-systems-theory","display_name":"Dynamical systems theory","score":0.4392600953578949},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42327573895454407},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.41484513878822327},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13281431794166565},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08943837881088257}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8285393714904785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8070540428161621},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7408882975578308},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7380691766738892},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.609312117099762},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5926617383956909},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5714809894561768},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5568724274635315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5110749006271362},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.46098455786705017},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44655197858810425},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.4392600953578949},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42327573895454407},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.41484513878822327},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13281431794166565},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08943837881088257},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9683009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683009","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1746819321","https://openalex.org/W1981530182","https://openalex.org/W2018087463","https://openalex.org/W2604763608","https://openalex.org/W2614367549","https://openalex.org/W2736601468","https://openalex.org/W2808809512","https://openalex.org/W2914086653","https://openalex.org/W2954737642","https://openalex.org/W2963306862","https://openalex.org/W3005787005","https://openalex.org/W3015606043","https://openalex.org/W3105951489","https://openalex.org/W3132132679","https://openalex.org/W3163842339","https://openalex.org/W3197314723","https://openalex.org/W4211049957","https://openalex.org/W4248908364","https://openalex.org/W4297800546","https://openalex.org/W4297813707","https://openalex.org/W6629804754","https://openalex.org/W6645550903","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6751797489","https://openalex.org/W6765145614","https://openalex.org/W6774352360","https://openalex.org/W6776331362","https://openalex.org/W6791336899"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W4241418540","https://openalex.org/W3130669838","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2891227010"],"abstract_inverted_index":{"While":[0],"conventional":[1],"reinforcement":[2],"learning":[3],"focuses":[4],"on":[5,176],"designing":[6,21],"agents":[7,22],"that":[8,23,34,68,74],"can":[9,24,69],"perform":[10],"one":[11],"task,":[12],"meta-learning":[13],"aims,":[14],"instead,":[15],"to":[16,26,71,90,119,126,132,160],"solve":[17],"the":[18,39,42,52,79,97,101,121,130,138,146,149,162,168,177,180,186],"problem":[19,53],"of":[20,44,54,94,114,137,148,179,188],"generalize":[25,70],"different":[27],"tasks":[28,73],"(e.g.,":[29],"environments,":[30],"obstacles,":[31],"and":[32,116,157,164,184],"goals)":[33],"were":[35,75],"not":[36,76],"considered":[37],"during":[38,96],"design":[40],"or":[41],"training":[43,55,80,98],"these":[45],"agents.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"consider":[51],"a":[56,92,112,134],"provably":[57],"safe":[58],"Neural":[59],"Network":[60],"(NN)":[61],"controller":[62,183],"for":[63],"uncertain":[64],"nonlinear":[65,139],"dynamical":[66,140],"systems":[67],"new":[72],"present":[77],"in":[78],"data":[81],"while":[82],"preserving":[83],"strong":[84],"safety":[85],"guarantees.":[86],"Our":[87],"approach":[88,128,190],"is":[89,129,158],"learn":[91],"set":[93],"NNs":[95,115,163],"phase.":[99],"When":[100],"task":[102,169],"becomes":[103,170],"available":[104],"at":[105],"runtime,":[106],"our":[107,127,189],"framework":[108],"will":[109],"carefully":[110],"select":[111],"subset":[113],"compose":[117,165],"them":[118,166],"form":[120],"final":[122],"NN":[123,155,182],"controller.":[124],"Critical":[125],"ability":[131],"compute":[133],"finite-state":[135],"abstraction":[136],"system.":[141],"This":[142],"abstract":[143],"model":[144],"captures":[145],"behavior":[147],"closed-loop":[150],"system":[151],"under":[152],"all":[153],"possible":[154],"weights,":[156],"used":[159],"train":[161],"when":[167],"available.":[171],"We":[172],"provide":[173],"theoretical":[174],"guarantees":[175],"correctness":[178],"resulting":[181],"show":[185],"efficacy":[187],"via":[191],"simulations.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}