{"id":"https://openalex.org/W4367016230","doi":"https://doi.org/10.1109/tse.2023.3269804","title":"A Search-Based Testing Approach for Deep Reinforcement Learning Agents","display_name":"A Search-Based Testing Approach for Deep Reinforcement Learning Agents","publication_year":2023,"publication_date":"2023-04-25","ids":{"openalex":"https://openalex.org/W4367016230","doi":"https://doi.org/10.1109/tse.2023.3269804"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2023.3269804","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tse.2023.3269804","pdf_url":"https://ieeexplore.ieee.org/ielx7/32/4359463/10107813.pdf","source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/32/4359463/10107813.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043379660","display_name":"Amirhossein Zolfagharian","orcid":"https://orcid.org/0000-0002-2411-7938"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amirhossein Zolfagharian","raw_affiliation_strings":["School of Electrical Engineering and Computer Science (EECS), University of Ottawa, Ottawa, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2411-7938","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science (EECS), University of Ottawa, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076024236","display_name":"Manel Abdellatif","orcid":"https://orcid.org/0000-0002-8647-1676"},"institutions":[{"id":"https://openalex.org/I9736820","display_name":"\u00c9cole de Technologie Sup\u00e9rieure","ror":"https://ror.org/0020snb74","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Manel Abdellatif","raw_affiliation_strings":["Software and Information Technology Engineering Department, École de Technologie Supérieure, Montreal, QC, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8647-1676","affiliations":[{"raw_affiliation_string":"Software and Information Technology Engineering Department, École de Technologie Supérieure, Montreal, QC, Canada","institution_ids":["https://openalex.org/I9736820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078533117","display_name":"Lionel Briand","orcid":"https://orcid.org/0000-0002-1393-1010"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]},{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["CA","LU"],"is_corresponding":false,"raw_author_name":"Lionel C. Briand","raw_affiliation_strings":["School of Electrical Engineering and Computer Science (EECS), University of Ottawa, Ottawa, ON, Canada","SnT Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0002-1393-1010","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science (EECS), University of Ottawa, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I153718931"]},{"raw_affiliation_string":"SnT Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016491411","display_name":"Mojtaba Bagherzadeh","orcid":"https://orcid.org/0000-0002-0253-671X"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]},{"id":"https://openalex.org/I4210127351","display_name":"Cisco Systems (Canada)","ror":"https://ror.org/02af0qw97","country_code":"CA","type":"company","lineage":["https://openalex.org/I135428043","https://openalex.org/I4210127351"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mojtaba Bagherzadeh","raw_affiliation_strings":["Cisco, Ottawa, ON, Canada","School of EECS, University of Ottawa, Ottawa, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0253-671X","affiliations":[{"raw_affiliation_string":"Cisco, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I4210127351"]},{"raw_affiliation_string":"School of EECS, University of Ottawa, Ottawa, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011292468","display_name":"S. Ramesh","orcid":"https://orcid.org/0000-0002-8501-7447"},"institutions":[{"id":"https://openalex.org/I118136607","display_name":"General Motors (United States)","ror":"https://ror.org/05addee68","country_code":"US","type":"company","lineage":["https://openalex.org/I118136607"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramesh S","raw_affiliation_strings":["Department of Research and Development, General Motors, Warren, MI, USA"],"raw_orcid":"https://orcid.org/0000-0002-8501-7447","affiliations":[{"raw_affiliation_string":"Department of Research and Development, General Motors, Warren, MI, USA","institution_ids":["https://openalex.org/I118136607"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.9313,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.97970829,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"49","issue":"7","first_page":"3715","last_page":"3735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9984999895095825,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/computer-science","display_name":"Computer science","score":0.8431433439254761},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7499356865882874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5029134154319763},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4721180200576782},{"id":"https://openalex.org/keywords/software-testing","display_name":"Software testing","score":0.44770434498786926},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.37048694491386414},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.34364795684814453},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.15915074944496155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431433439254761},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7499356865882874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5029134154319763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4721180200576782},{"id":"https://openalex.org/C2984328558","wikidata":"https://www.wikidata.org/wiki/Q188522","display_name":"Software testing","level":3,"score":0.44770434498786926},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.37048694491386414},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34364795684814453},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.15915074944496155}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tse.2023.3269804","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tse.2023.3269804","pdf_url":"https://ieeexplore.ieee.org/ielx7/32/4359463/10107813.pdf","source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:espace2.etsmtl.ca:26801","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402392","display_name":"Espace \u00c9TS (ETS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1341030882","host_organization_name":"Educational Testing Service","host_organization_lineage":["https://openalex.org/I1341030882"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article publi\u00e9 dans une revue, r\u00e9vis\u00e9 par les pairs"}],"best_oa_location":{"id":"doi:10.1109/tse.2023.3269804","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tse.2023.3269804","pdf_url":"https://ieeexplore.ieee.org/ielx7/32/4359463/10107813.pdf","source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367016230.pdf","grobid_xml":"https://content.openalex.org/works/W4367016230.grobid-xml"},"referenced_works_count":82,"referenced_works":["https://openalex.org/W1577581905","https://openalex.org/W1589038126","https://openalex.org/W1599808047","https://openalex.org/W1966723285","https://openalex.org/W1977655452","https://openalex.org/W1993131108","https://openalex.org/W2017716425","https://openalex.org/W2047094503","https://openalex.org/W2098118819","https://openalex.org/W2101786389","https://openalex.org/W2118246375","https://openalex.org/W2118382442","https://openalex.org/W2126105956","https://openalex.org/W2150468603","https://openalex.org/W2397240726","https://openalex.org/W2543927648","https://openalex.org/W2573137292","https://openalex.org/W2592857946","https://openalex.org/W2746553466","https://openalex.org/W2753944351","https://openalex.org/W2775408020","https://openalex.org/W2775998942","https://openalex.org/W2804337238","https://openalex.org/W2807499323","https://openalex.org/W2899685447","https://openalex.org/W2911964244","https://openalex.org/W2941205169","https://openalex.org/W2948508308","https://openalex.org/W2948727232","https://openalex.org/W2949103145","https://openalex.org/W2953746822","https://openalex.org/W2957905354","https://openalex.org/W2963327228","https://openalex.org/W2963857521","https://openalex.org/W2963913218","https://openalex.org/W2982138961","https://openalex.org/W3003546983","https://openalex.org/W3042729974","https://openalex.org/W3045875028","https://openalex.org/W3046870880","https://openalex.org/W3089213640","https://openalex.org/W3089366133","https://openalex.org/W3103014337","https://openalex.org/W3105400121","https://openalex.org/W3120394327","https://openalex.org/W3121342653","https://openalex.org/W3145910327","https://openalex.org/W3164878287","https://openalex.org/W3165441654","https://openalex.org/W3181437774","https://openalex.org/W3192124410","https://openalex.org/W3195835426","https://openalex.org/W3200885897","https://openalex.org/W3207426388","https://openalex.org/W4211209837","https://openalex.org/W4213251304","https://openalex.org/W4214717370","https://openalex.org/W4231702991","https://openalex.org/W4241119678","https://openalex.org/W4285601900","https://openalex.org/W4287327356","https://openalex.org/W4297792190","https://openalex.org/W4298857966","https://openalex.org/W4301602852","https://openalex.org/W4319663674","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6712173889","https://openalex.org/W6733049761","https://openalex.org/W6737897983","https://openalex.org/W6746973458","https://openalex.org/W6747027214","https://openalex.org/W6752255449","https://openalex.org/W6763944474","https://openalex.org/W6764031673","https://openalex.org/W6774966973","https://openalex.org/W6775850705","https://openalex.org/W6781640943","https://openalex.org/W6791196043","https://openalex.org/W6803471652"],"related_works":["https://openalex.org/W2090301720","https://openalex.org/W2008194781","https://openalex.org/W3176274227","https://openalex.org/W3089971865","https://openalex.org/W2039512252","https://openalex.org/W2038209453","https://openalex.org/W2913502950","https://openalex.org/W1916954724","https://openalex.org/W2914660298","https://openalex.org/W2122084118"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1,191],"Learning":[2,192],"(DRL)":[3],"algorithms":[4,28],"have":[5,29],"been":[6],"increasingly":[7],"employed":[8],"during":[9,74],"the":[10,53,57,79,114,125,134,142,145,154,161,168,197,210,230,243,276,291,305,309,315],"last":[11],"decade":[12],"to":[13,47,55,63,66,71,89,95,121,132,150,153,195,228,275,283,303],"solve":[14],"various":[15],"decision-making":[16],"problems":[17,257],"such":[18,117],"as":[19,260],"autonomous":[20],"driving,":[21],"trading":[22],"decisions,":[23],"and":[24,93,167,223,239,262,312],"robotics.":[25],"However,":[26,116],"these":[27],"faced":[30],"great":[31],"challenges":[32],"when":[33],"deployed":[34],"in":[35],"safety-critical":[36],"environments":[37],"since":[38],"they":[39],"often":[40,119],"exhibit":[41],"erroneous":[42],"behaviors":[43],"that":[44,108,264,286],"can":[45,84,300],"lead":[46,120],"potentially":[48],"critical":[49,72],"errors.":[50],"One":[51],"of":[52,59,81,113,124,136,144,158,164,171,176,190,199,209,237,290,317],"ways":[54],"assess":[56,314],"safety":[58,96],"DRL":[60,87,103,137,159,172,177,201,244,292],"agents":[61,104,138,178,251],"is":[62,131,179],"test":[64,86,133,165,196],"them":[65],"detect":[67],"possible":[68],"faults":[69,273],"leading":[70],"failures":[73],"their":[75,91,128],"execution.":[76],"This":[77],"raises":[78],"question":[80],"how":[82,282],"we":[83,184],"efficiently":[85],"policies":[88,147],"ensure":[90],"correctness":[92],"adherence":[94],"requirements.":[97,151],"Most":[98],"existing":[99],"works":[100],"on":[101,219,249,253],"testing":[102,141,175,215],"use":[105],"adversarial":[106],"attacks":[107,118],"perturb":[109],"states":[110,123,238],"or":[111],"actions":[112,240],"agent.":[115],"unrealistic":[122],"environment.":[126],"Furthermore,":[127],"main":[129],"goal":[130],"robustness":[135],"rather":[139],"than":[140],"compliance":[143],"agents'":[146],"with":[148],"respect":[149],"Due":[152],"huge":[155],"state":[156],"space":[157],"environments,":[160],"high":[162],"cost":[163],"execution,":[166],"black-box":[169],"nature":[170],"algorithms,":[173],"exhaustive":[174],"impossible.":[180],"In":[181],"this":[182],"paper,":[183],"propose":[185],"a":[186,200,213,224],"Search-based":[187],"Testing":[188,269],"Approach":[189],"Agents":[193],"(STARLA)":[194],"policy":[198],"agent":[202,211,293,310],"by":[203,242,270],"effectively":[204],"searching":[205],"for":[206],"failing":[207],"executions":[208],"within":[212],"limited":[214],"budget.":[216],"We":[217,246,279],"rely":[218],"machine":[220],"learning":[221],"models":[222],"dedicated":[225],"genetic":[226],"algorithm":[227],"narrow":[229],"search":[231,296],"toward":[232],"faulty":[233,288],"episodes":[234,289],"(i.e.,":[235],"sequences":[236],"produced":[241],"agent).":[245],"apply":[247],"STARLA":[248,265],"Deep-Q-Learning":[250],"trained":[252],"two":[254],"different":[255],"RL":[256],"widely":[258],"used":[259,302],"benchmarks":[261],"show":[263],"significantly":[266],"outperforms":[267],"Random":[268],"detecting":[271],"more":[272],"related":[274],"agent's":[277],"policy.":[278],"also":[280],"investigate":[281],"extract":[284],"rules":[285,299],"characterize":[287],"using":[294],"our":[295],"results.":[297],"Such":[298],"be":[301],"understand":[304],"conditions":[306],"under":[307],"which":[308],"fails":[311],"thus":[313],"risks":[316],"deploying":[318],"it.":[319]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}