{"id":"https://openalex.org/W3200761006","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533410","title":"Non-divergent Imitation for Verification of Complex Learned Controllers","display_name":"Non-divergent Imitation for Verification of Complex Learned Controllers","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200761006","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533410","mag":"3200761006"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5035017701","display_name":"Vahdat Abdelzad","orcid":"https://orcid.org/0000-0002-8658-2712"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vahdat Abdelzad","raw_affiliation_strings":["University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334542","display_name":"Jaeyoung Lee","orcid":"https://orcid.org/0000-0003-4390-7676"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jaeyoung Lee","raw_affiliation_strings":["University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081670169","display_name":"Sean Sedwards","orcid":"https://orcid.org/0000-0002-2903-0823"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sean Sedwards","raw_affiliation_strings":["University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005357290","display_name":"Soheil Soltani","orcid":"https://orcid.org/0000-0002-7223-8136"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Soheil Soltani","raw_affiliation_strings":["University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066916130","display_name":"Krzysztof Czarnecki","orcid":"https://orcid.org/0000-0003-1642-1101"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Krzysztof Czarnecki","raw_affiliation_strings":["University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.1465,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39898112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"32","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9977999925613403,"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":0.9873999953269958,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.6944663524627686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6829562783241272},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.6079955101013184},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5759215950965881},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5721518397331238},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5560725927352905},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5553937554359436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.380456805229187},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3452202081680298},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3292929530143738},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22101128101348877},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09775260090827942}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6944663524627686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829562783241272},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6079955101013184},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5759215950965881},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5721518397331238},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5560725927352905},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5553937554359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.380456805229187},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3452202081680298},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3292929530143738},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22101128101348877},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09775260090827942},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1480909796","https://openalex.org/W1594031697","https://openalex.org/W1600437712","https://openalex.org/W1931877416","https://openalex.org/W2091565802","https://openalex.org/W2101234009","https://openalex.org/W2121863487","https://openalex.org/W2142641780","https://openalex.org/W2145339207","https://openalex.org/W2594877703","https://openalex.org/W2803974723","https://openalex.org/W2912640545","https://openalex.org/W2951544639","https://openalex.org/W2953466973","https://openalex.org/W2962957031","https://openalex.org/W2963673089","https://openalex.org/W2964231903","https://openalex.org/W2990881605","https://openalex.org/W3012300836","https://openalex.org/W3037598048","https://openalex.org/W3043641198","https://openalex.org/W3089538634","https://openalex.org/W3090729135","https://openalex.org/W3102502161","https://openalex.org/W3104371626","https://openalex.org/W3104579376","https://openalex.org/W4205950066","https://openalex.org/W4214717370","https://openalex.org/W4288283627","https://openalex.org/W6640174482","https://openalex.org/W6675354045","https://openalex.org/W6680724558","https://openalex.org/W6734921443","https://openalex.org/W6751437432","https://openalex.org/W6760757228","https://openalex.org/W6764309396","https://openalex.org/W6769214901","https://openalex.org/W6780120684","https://openalex.org/W6783268431"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W3110702597","https://openalex.org/W2078761926","https://openalex.org/W2110441383","https://openalex.org/W2125620709","https://openalex.org/W3125091513","https://openalex.org/W1498872724","https://openalex.org/W2996999409"],"abstract_inverted_index":{"We":[0,39,63,82],"consider":[1],"the":[2,19,29,90],"problem":[3],"of":[4,31,85,92],"verifying":[5],"complex":[6],"learned":[7],"controllers":[8,98],"using":[9],"distillation.":[10],"In":[11],"contrast":[12],"to":[13],"previous":[14],"work,":[15],"we":[16],"require":[17],"that":[18,41,69,104],"distilled":[20],"model":[21],"maintains":[22],"behavioural":[23,61],"fidelity":[24],"with":[25,45],"an":[26],"oracle,":[27],"defining":[28],"notion":[30],"non-divergent":[32],"path":[33],"length":[34],"(NPL)":[35],"as":[36],"a":[37,66],"metric.":[38],"demonstrate":[40,89],"current":[42],"distillation":[43,67],"approaches":[44],"proven":[46],"accuracy":[47],"bounds":[48],"do":[49],"not":[50],"have":[51,105],"high":[52],"expected":[53,73],"NPL":[54,86],"and":[55,78,88,113],"can":[56],"be":[57],"out-performed":[58],"by":[59],"naive":[60],"cloning.":[62],"thus":[64],"propose":[65],"algorithm":[68,94],"typically":[70],"gives":[71],"greater":[72],"NPL,":[74],"improved":[75],"sample":[76],"efficiency,":[77],"more":[79],"compact":[80],"models.":[81],"prove":[83],"properties":[84],"maximization":[87],"performance":[91],"our":[93],"on":[95],"deep":[96],"Q-network":[97],"for":[99],"three":[100],"standard":[101],"learning":[102],"environments":[103],"been":[106],"used":[107],"in":[108],"this":[109],"context:":[110],"Pong,":[111],"CartPole":[112],"MountainCar.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}