{"id":"https://openalex.org/W4391579648","doi":"https://doi.org/10.1145/3597503.3623311","title":"Learning and Repair of Deep Reinforcement Learning Policies from Fuzz-Testing Data","display_name":"Learning and Repair of Deep Reinforcement Learning Policies from Fuzz-Testing Data","publication_year":2024,"publication_date":"2024-02-06","ids":{"openalex":"https://openalex.org/W4391579648","doi":"https://doi.org/10.1145/3597503.3623311"},"language":"en","primary_location":{"id":"doi:10.1145/3597503.3623311","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597503.3623311","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597503.3623311","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3597503.3623311","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078635542","display_name":"Martin Tappler","orcid":"https://orcid.org/0000-0002-4193-5609"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]},{"id":"https://openalex.org/I4210123126","display_name":"Silicon Austria Labs (Austria)","ror":"https://ror.org/03b1qgn79","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210123126"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Martin Tappler","raw_affiliation_strings":["Institute of Software Technology, Graz University of Technology, Graz, Austria","TU Graz - SAL, DES Lab, Silicon Austria Labs, Graz, Austria","Institute of Software Technology, Graz University of Technology, Graz, Austria TU Graz - SAL, DES Lab, Silicon Austria Labs, Graz, Austria"],"raw_orcid":"https://orcid.org/0000-0002-4193-5609","affiliations":[{"raw_affiliation_string":"Institute of Software Technology, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"TU Graz - SAL, DES Lab, Silicon Austria Labs, Graz, Austria","institution_ids":["https://openalex.org/I4092182","https://openalex.org/I4210123126"]},{"raw_affiliation_string":"Institute of Software Technology, Graz University of Technology, Graz, Austria TU Graz - SAL, DES Lab, Silicon Austria Labs, Graz, Austria","institution_ids":["https://openalex.org/I4092182","https://openalex.org/I4210123126"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016658007","display_name":"Andrea Pferscher","orcid":"https://orcid.org/0000-0002-9446-9541"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Andrea Pferscher","raw_affiliation_strings":["Institute of Software Technology, Graz University of Technology, Graz, Austria"],"raw_orcid":"https://orcid.org/0000-0002-9446-9541","affiliations":[{"raw_affiliation_string":"Institute of Software Technology, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009450062","display_name":"Bernhard K. Aichernig","orcid":"https://orcid.org/0000-0002-3484-5584"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Bernhard K. Aichernig","raw_affiliation_strings":["Institute of Software Technology, Graz University of Technology, Graz, Austria"],"raw_orcid":"https://orcid.org/0000-0002-3484-5584","affiliations":[{"raw_affiliation_string":"Institute of Software Technology, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042655793","display_name":"Bettina K\u00f6nighofer","orcid":"https://orcid.org/0000-0001-5183-5452"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Bettina K\u00f6nighofer","raw_affiliation_strings":["Institute of Applied Information Processing and Communications, Graz University of Technology, Graz, Austria"],"raw_orcid":"https://orcid.org/0000-0001-5183-5452","affiliations":[{"raw_affiliation_string":"Institute of Applied Information Processing and Communications, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9966999888420105,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9889000058174133,"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":0.8133560419082642},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6497457027435303},{"id":"https://openalex.org/keywords/fuzz-testing","display_name":"Fuzz testing","score":0.5692821741104126},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.46966493129730225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4186156690120697},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16988828778266907},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05805450677871704},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.055459022521972656}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8133560419082642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6497457027435303},{"id":"https://openalex.org/C111065885","wikidata":"https://www.wikidata.org/wiki/Q1189053","display_name":"Fuzz testing","level":3,"score":0.5692821741104126},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46966493129730225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4186156690120697},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16988828778266907},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05805450677871704},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.055459022521972656},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3597503.3623311","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597503.3623311","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597503.3623311","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3597503.3623311","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597503.3623311","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597503.3623311","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6618363488","display_name":null,"funder_award_id":"101007350","funder_id":"https://openalex.org/F4320327207","funder_display_name":"Electronic Components and Systems for European Leadership"},{"id":"https://openalex.org/G7775410883","display_name":"AI-augmented automation for efficient DevOps, a model-based framework for continuous development At RunTime in cyber-physical systems","funder_award_id":"101007350","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320310430","display_name":"TU Graz, Internationale Beziehungen und Mobilit\u00e4tsprogramme","ror":"https://ror.org/00d7xrm67"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320326047","display_name":"Amt der Steierm\u00e4rkischen Landesregierung","ror":null},{"id":"https://openalex.org/F4320327207","display_name":"Electronic Components and Systems for European Leadership","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391579648.pdf","grobid_xml":"https://content.openalex.org/works/W4391579648.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W106792269","https://openalex.org/W2145339207","https://openalex.org/W2164114810","https://openalex.org/W2257979135","https://openalex.org/W2473930607","https://openalex.org/W2560674852","https://openalex.org/W2746553466","https://openalex.org/W2747329762","https://openalex.org/W2788862220","https://openalex.org/W2877093712","https://openalex.org/W2883184365","https://openalex.org/W2903242674","https://openalex.org/W2957905354","https://openalex.org/W2963327228","https://openalex.org/W2963411833","https://openalex.org/W2972500268","https://openalex.org/W2980221379","https://openalex.org/W2982316857","https://openalex.org/W2982852993","https://openalex.org/W2996367417","https://openalex.org/W2998396902","https://openalex.org/W3003852841","https://openalex.org/W3083905601","https://openalex.org/W3124518196","https://openalex.org/W3139531864","https://openalex.org/W3173591235","https://openalex.org/W3206820790","https://openalex.org/W4225507135","https://openalex.org/W4244452926","https://openalex.org/W4253074907","https://openalex.org/W4283070108","https://openalex.org/W4283816176","https://openalex.org/W4285601900","https://openalex.org/W4292265058","https://openalex.org/W6920557064"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2511770387","https://openalex.org/W3120811337","https://openalex.org/W3203597304","https://openalex.org/W4385301282","https://openalex.org/W2990186179","https://openalex.org/W4248424560","https://openalex.org/W3023977444","https://openalex.org/W2766647240","https://openalex.org/W4210660460"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,16,19],"from":[2,20,40,86],"demonstrations":[3,22,85,96,105,136],"(RLfD)":[4],"is":[5,132,157],"a":[6,35,92],"promising":[7],"approach":[8],"to":[9,25,48,58,147,159],"improve":[10],"the":[11,28,46,50,81,103,110,115,125,149],"exploration":[12],"efficiency":[13],"of":[14,52,54,78,84,95,114],"reinforcement":[15],"(RL)":[17],"by":[18],"expert":[21,169],"in":[23,124],"addition":[24],"interactions":[26],"with":[27,43,45],"environment.":[29,127],"In":[30],"this":[31],"paper,":[32],"we":[33,66,89,119,134],"propose":[34],"framework":[36,156],"that":[37,140,154],"combines":[38],"techniques":[39],"search-based":[41,98],"testing":[42,139],"RLfD":[44],"goal":[47],"raise":[49],"level":[51],"dependability":[53],"RL":[55,75,117],"policies":[56,165],"and":[57,73,101,112,144,163],"reduce":[59],"human":[60],"engineering":[61],"effort.":[62],"Within":[63],"our":[64,155],"framework,":[65],"provide":[67],"methods":[68,100],"for":[69,106,121],"efficiently":[70,160],"training,":[71],"evaluating,":[72],"repairing":[74],"policies.":[76],"Instead":[77],"relying":[79],"on":[80],"costly":[82],"collection":[83],"(human)":[87],"experts,":[88],"automatically":[90],"compute":[91,135],"diverse":[93],"set":[94],"via":[97],"fuzzing":[99],"use":[102,145],"fuzz":[104,138],"RLfD.":[107],"To":[108],"evaluate":[109],"safety":[111],"robustness":[113],"trained":[116],"agent,":[118],"search":[120],"safety-critical":[122],"scenarios":[123],"black-box":[126],"Finally,":[128],"when":[129],"unsafe":[130],"behavior":[131,143],"detected,":[133],"through":[137],"represent":[141],"safe":[142,164],"them":[146],"repair":[148],"policy.":[150],"Our":[151],"experiments":[152],"show":[153],"able":[158],"learn":[161],"high-performing":[162],"without":[166],"requiring":[167],"any":[168],"knowledge.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}