{"id":"https://openalex.org/W4297632799","doi":"https://doi.org/10.1145/3547276.3548635","title":"Training reinforcement learning models via an adversarial evolutionary algorithm","display_name":"Training reinforcement learning models via an adversarial evolutionary algorithm","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4297632799","doi":"https://doi.org/10.1145/3547276.3548635"},"language":"en","primary_location":{"id":"doi:10.1145/3547276.3548635","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3547276.3548635","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3547276.3548635","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","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/10.1145/3547276.3548635","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068431797","display_name":"Mark Coletti","orcid":"https://orcid.org/0000-0003-1020-531X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Coletti","raw_affiliation_strings":["Oak Ridge National Laboratory, United States of America","ORNL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, United States of America","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"ORNL","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070225814","display_name":"Chathika Gunaratne","orcid":"https://orcid.org/0000-0002-2508-8745"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chathika Gunaratne","raw_affiliation_strings":["Oak Ridge National Laboratory, United States of America","ORNL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, United States of America","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"ORNL","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033784578","display_name":"Catherine D. Schuman","orcid":"https://orcid.org/0000-0002-4264-8097"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Catherine Schuman","raw_affiliation_strings":["University of Tennessee, United States of America","University of Tennessee, Knoxville (UTK)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, United States of America","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee, Knoxville (UTK)","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021986280","display_name":"Robert M. Patton","orcid":"https://orcid.org/0000-0002-8101-0571"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Patton","raw_affiliation_strings":["Oak Ridge National Laboratory, United States of America","ORNL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, United States of America","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"ORNL","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10969314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7038999795913696,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7038999795913696,"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":0.6758999824523926,"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/adversarial-system","display_name":"Adversarial system","score":0.8323104381561279},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7672054767608643},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6963813304901123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6092665195465088},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5796999335289001},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.4683729112148285},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45203012228012085},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.43306270241737366},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3576437830924988}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8323104381561279},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7672054767608643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6963813304901123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6092665195465088},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5796999335289001},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.4683729112148285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45203012228012085},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.43306270241737366},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3576437830924988},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3547276.3548635","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3547276.3548635","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3547276.3548635","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1885310","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1885310","pdf_url":"https://www.osti.gov/servlets/purl/1885310","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"doi:10.1145/3547276.3548635","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3547276.3548635","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3547276.3548635","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G121915436","display_name":null,"funder_award_id":"DEAC05- 00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G203625172","display_name":null,"funder_award_id":"DE--AC05--00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2988778103","display_name":null,"funder_award_id":"DE-AC05?","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G675320460","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297632799.pdf","grobid_xml":"https://content.openalex.org/works/W4297632799.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1557517019","https://openalex.org/W2091565802","https://openalex.org/W2112036188","https://openalex.org/W2126527976","https://openalex.org/W2250904038","https://openalex.org/W2489708883","https://openalex.org/W2767077319","https://openalex.org/W2791729947","https://openalex.org/W2935588605","https://openalex.org/W2962718684","https://openalex.org/W2997293639","https://openalex.org/W3038093235","https://openalex.org/W3123045479","https://openalex.org/W3182790013","https://openalex.org/W4200596413"],"related_works":["https://openalex.org/W2130703626","https://openalex.org/W4297582752","https://openalex.org/W4285805405","https://openalex.org/W85101999","https://openalex.org/W2391924736","https://openalex.org/W3133779647","https://openalex.org/W4291270682","https://openalex.org/W1560122427","https://openalex.org/W2593449396","https://openalex.org/W2780789525"],"abstract_inverted_index":{"When":[0],"training":[1,9,22,35,55,131],"for":[2,30,76],"control":[3],"problems,":[4],"more":[5,16,21],"episodes":[6,17,36,128],"used":[7],"in":[8,53,87,130],"usually":[10],"leads":[11],"to":[12,70,133],"better":[13],"generalizability,":[14],"but":[15,47],"also":[18],"requires":[19],"significantly":[20],"time.":[23],"There":[24],"are":[25,37],"a":[26,77],"variety":[27],"of":[28,91,100,127],"approaches":[29],"selecting":[31],"the":[32,54,72,88,97,110,118,125],"way":[33],"that":[34,64,117],"chosen,":[38],"including":[39],"fixed":[40],"episodes,":[41],"uniform":[42],"sampling,":[43,46,141],"and":[44,142],"stochastic":[45,140],"they":[48],"can":[49],"all":[50],"leave":[51],"gaps":[52],"landscape.":[56],"In":[57],"this":[58,107],"work,":[59],"we":[60],"describe":[61],"an":[62,66],"approach":[63,108],"leverages":[65],"adversarial":[67,119],"evolutionary":[68,120],"algorithm":[69,121],"identify":[71],"worst":[73],"performing":[74],"states":[75,86],"given":[78],"model.":[79],"We":[80,105,115],"then":[81],"use":[82],"information":[83],"about":[84],"these":[85],"next":[89],"cycle":[90],"training,":[92],"which":[93],"is":[94,103],"repeated":[95],"until":[96],"desired":[98],"level":[99],"model":[101,135],"performance":[102],"met.":[104],"demonstrate":[106],"with":[109,139],"OpenAI":[111],"Gym":[112],"cart-pole":[113],"problem.":[114],"show":[116],"did":[122],"not":[123],"reduce":[124],"number":[126],"required":[129],"needed":[132],"attain":[134],"generalizability":[136],"when":[137],"compared":[138],"actually":[143],"performed":[144],"slightly":[145],"worse.":[146]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}