{"id":"https://openalex.org/W3094455834","doi":"https://doi.org/10.23919/acc50511.2021.9483182","title":"Safe Reinforcement Learning with Nonlinear Dynamics via Model Predictive Shielding","display_name":"Safe Reinforcement Learning with Nonlinear Dynamics via Model Predictive Shielding","publication_year":2021,"publication_date":"2021-05-25","ids":{"openalex":"https://openalex.org/W3094455834","doi":"https://doi.org/10.23919/acc50511.2021.9483182","mag":"3094455834"},"language":"en","primary_location":{"id":"doi:10.23919/acc50511.2021.9483182","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9483182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.10691","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029243071","display_name":"Osbert Bastani","orcid":"https://orcid.org/0000-0001-9990-7566"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Osbert Bastani","raw_affiliation_strings":["Deapartment of Computer and Information Science, University of Pennsylvania","University of Pennsylvania,Deapartment of Computer and Information Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deapartment of Computer and Information Science, University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"University of Pennsylvania,Deapartment of Computer and Information Science","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5029243071"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3488","last_page":"3494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996399998664856,"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":0.996399998664856,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9958000183105469,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.698482096195221},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.6859319806098938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6101527214050293},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5508034229278564},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5476318001747131},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5282118916511536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5117378234863281},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5033714175224304},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4908784031867981},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.44271039962768555},{"id":"https://openalex.org/keywords/electromagnetic-shielding","display_name":"Electromagnetic shielding","score":0.42492881417274475},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.33803850412368774},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22911876440048218},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.20476242899894714},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.13046252727508545},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.08518490195274353},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.08135822415351868}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.698482096195221},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.6859319806098938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6101527214050293},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5508034229278564},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5476318001747131},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5282118916511536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5117378234863281},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5033714175224304},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4908784031867981},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.44271039962768555},{"id":"https://openalex.org/C2265751","wikidata":"https://www.wikidata.org/wiki/Q332007","display_name":"Electromagnetic shielding","level":2,"score":0.42492881417274475},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.33803850412368774},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22911876440048218},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.20476242899894714},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.13046252727508545},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.08518490195274353},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.08135822415351868},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.23919/acc50511.2021.9483182","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9483182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.10691","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.10691","pdf_url":"https://arxiv.org/pdf/1905.10691","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"},{"id":"mag:3094455834","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1905.10691.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1905.10691","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.10691","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.10691","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.10691","pdf_url":"https://arxiv.org/pdf/1905.10691","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":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3094455834.pdf","grobid_xml":"https://content.openalex.org/works/W3094455834.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W1963790880","https://openalex.org/W1993210515","https://openalex.org/W2053572490","https://openalex.org/W2091565802","https://openalex.org/W2104733512","https://openalex.org/W2133404041","https://openalex.org/W2151237105","https://openalex.org/W2164479831","https://openalex.org/W2296356821","https://openalex.org/W2462906003","https://openalex.org/W2618318883","https://openalex.org/W2796284132","https://openalex.org/W2889696653","https://openalex.org/W2892521964","https://openalex.org/W2914526782","https://openalex.org/W2953466973","https://openalex.org/W2962775887","https://openalex.org/W2962803570","https://openalex.org/W2963575966","https://openalex.org/W2963958573","https://openalex.org/W2964130946","https://openalex.org/W2964231903","https://openalex.org/W2964340170","https://openalex.org/W2973076431","https://openalex.org/W2990747716","https://openalex.org/W3031236342","https://openalex.org/W3037935411","https://openalex.org/W3104371626","https://openalex.org/W3120459386","https://openalex.org/W6639175102","https://openalex.org/W6675999342","https://openalex.org/W6682367392","https://openalex.org/W6684037837","https://openalex.org/W6717915398","https://openalex.org/W6718836005","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6749992176","https://openalex.org/W6751437432","https://openalex.org/W6751535212","https://openalex.org/W6754113743","https://openalex.org/W6754711207","https://openalex.org/W6759013911","https://openalex.org/W6759014971","https://openalex.org/W6765473059","https://openalex.org/W6766224423","https://openalex.org/W6770858630"],"related_works":["https://openalex.org/W3186708588","https://openalex.org/W3196308616","https://openalex.org/W3007196997","https://openalex.org/W3136988982","https://openalex.org/W2053572490","https://openalex.org/W2618318883","https://openalex.org/W2997735228","https://openalex.org/W3184253385","https://openalex.org/W2924156739","https://openalex.org/W3116714419","https://openalex.org/W3204099061","https://openalex.org/W3204849641","https://openalex.org/W3098476112","https://openalex.org/W3006225970","https://openalex.org/W3036821294","https://openalex.org/W3036501456","https://openalex.org/W3037396281","https://openalex.org/W3171392489","https://openalex.org/W2972914113","https://openalex.org/W3132818220"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"is":[2,16,57],"a":[3,26,61,67,84,88],"promising":[4],"approach":[5,98],"to":[6,18,58,91],"synthesizing":[7],"policies":[8],"for":[9],"challenging":[10],"robotics":[11],"tasks.":[12],"A":[13],"key":[14],"problem":[15],"how":[17],"ensure":[19,59,92],"safety":[20,69],"of":[21],"the":[22,47,50,55,106],"learned":[23,85],"policy-e.g.,":[24],"that":[25,34,60,80,96],"walking":[27],"robot":[28],"does":[29,38],"not":[30,39],"fall":[31],"over":[32],"or":[33],"an":[35,42,73],"autonomous":[36],"car":[37],"run":[40],"into":[41],"obstacle.":[43],"We":[44,71,94],"focus":[45],"on":[46,105],"setting":[48],"where":[49],"dynamics":[51],"are":[52],"known,":[53],"and":[54,87,101],"goal":[56],"policy":[62,86,90],"trained":[63],"in":[64],"simulation":[65],"satisfies":[66],"given":[68],"constraint.":[70],"propose":[72],"approach,":[74],"called":[75],"model":[76],"predictive":[77],"shielding":[78],"(MPS),":[79],"switches":[81],"on-the-fly":[82],"between":[83],"backup":[89],"safety.":[93],"prove":[95],"our":[97],"guarantees":[99],"safety,":[100],"empirically":[102],"evaluate":[103],"it":[104],"cart-pole.":[107]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}