{"id":"https://openalex.org/W4413311552","doi":"https://doi.org/10.1145/3729878.3746703","title":"Multi-parameter Control for the (1+(\u03bb, \u03bb))-GA on OneMax via Deep Reinforcement Learning","display_name":"Multi-parameter Control for the (1+(\u03bb, \u03bb))-GA on OneMax via Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-08-19","ids":{"openalex":"https://openalex.org/W4413311552","doi":"https://doi.org/10.1145/3729878.3746703"},"language":"en","primary_location":{"id":"doi:10.1145/3729878.3746703","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3729878.3746703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/SIGEVO Conference on Foundations of Genetic Algorithms","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.12982","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045979733","display_name":"Tai Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I16835326","display_name":"University of St Andrews","ror":"https://ror.org/02wn5qz54","country_code":"GB","type":"education","lineage":["https://openalex.org/I16835326"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR","GB"],"is_corresponding":false,"raw_author_name":"Tai Nguyen","raw_affiliation_strings":["University of St Andrews, St Andrews, United Kingdom, Sorbonne Universit\u00e9, CNRS, LIP6 Paris, France"],"raw_orcid":"https://orcid.org/0009-0004-7707-2069","affiliations":[{"raw_affiliation_string":"University of St Andrews, St Andrews, United Kingdom, Sorbonne Universit\u00e9, CNRS, LIP6 Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I1294671590","https://openalex.org/I16835326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111483525","display_name":"Phong Le","orcid":null},"institutions":[{"id":"https://openalex.org/I16835326","display_name":"University of St Andrews","ror":"https://ror.org/02wn5qz54","country_code":"GB","type":"education","lineage":["https://openalex.org/I16835326"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Phong Le","raw_affiliation_strings":["University of St Andrews, St Andrews, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0000-0749-9519","affiliations":[{"raw_affiliation_string":"University of St Andrews, St Andrews, United Kingdom","institution_ids":["https://openalex.org/I16835326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040561209","display_name":"Carola Doerr","orcid":"https://orcid.org/0000-0002-4981-3227"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210159731","display_name":"LIP6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Carola Doerr","raw_affiliation_strings":["Sorbonne Universit\u00e9, CNRS, LIP6, Paris, France"],"raw_orcid":"https://orcid.org/0000-0002-4981-3227","affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, CNRS, LIP6, Paris, France","institution_ids":["https://openalex.org/I4210159731","https://openalex.org/I204730241","https://openalex.org/I1294671590","https://openalex.org/I39804081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043650771","display_name":"Nguyen Dang","orcid":"https://orcid.org/0000-0002-2693-6953"},"institutions":[{"id":"https://openalex.org/I16835326","display_name":"University of St Andrews","ror":"https://ror.org/02wn5qz54","country_code":"GB","type":"education","lineage":["https://openalex.org/I16835326"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nguyen Dang","raw_affiliation_strings":["University of St Andrews, St Andrews, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-2693-6953","affiliations":[{"raw_affiliation_string":"University of St Andrews, St Andrews, United Kingdom","institution_ids":["https://openalex.org/I16835326"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.21569129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"190","last_page":"201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9587000012397766,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9587000012397766,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.958299994468689,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9513000249862671,"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":0.7693754434585571},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5989499092102051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5363354086875916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5173789262771606},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3337338864803314},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.310193806886673}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7693754434585571},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5989499092102051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5363354086875916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5173789262771606},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3337338864803314},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.310193806886673}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3729878.3746703","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3729878.3746703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/SIGEVO Conference on Foundations of Genetic Algorithms","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.12982","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12982","pdf_url":"https://arxiv.org/pdf/2505.12982","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05171396v1","is_oa":true,"landing_page_url":"https://hal.sorbonne-universite.fr/hal-05171396","pdf_url":"https://hal.sorbonne-universite.fr/hal-05171396v1/file/FOGA_2025_Multiparam_DAC_HAL.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Foundations of Genetic Algorithms XVIII (FOGA), ACM/SIGEVO, 2025, Leiden, Netherlands. ⟨10.1145/3729878.3746703⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.12982","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12982","pdf_url":"https://arxiv.org/pdf/2505.12982","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2125534567","display_name":"Dynamic Selection and Configuration of Black-box Optimization Algorithms","funder_award_id":"101125586","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6827053890","display_name":"Allier l'optimisation bo\u00eete noire et l'apprentissage automatique pour la configuration dynamiques d'algorithmes","funder_award_id":"ANR-23-CE23-0035","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413311552.pdf","grobid_xml":"https://content.openalex.org/works/W4413311552.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1557517019","https://openalex.org/W1971237725","https://openalex.org/W2024372894","https://openalex.org/W2027964569","https://openalex.org/W2029375893","https://openalex.org/W2035300004","https://openalex.org/W2081488245","https://openalex.org/W2088034357","https://openalex.org/W2110382857","https://openalex.org/W2141119792","https://openalex.org/W2146879413","https://openalex.org/W2190644555","https://openalex.org/W2512971201","https://openalex.org/W2605939683","https://openalex.org/W2742595244","https://openalex.org/W2746553466","https://openalex.org/W2754517384","https://openalex.org/W2769883686","https://openalex.org/W2797555254","https://openalex.org/W2887049521","https://openalex.org/W2935958147","https://openalex.org/W2955804429","https://openalex.org/W2962690183","https://openalex.org/W2969267791","https://openalex.org/W3016399834","https://openalex.org/W3090567565","https://openalex.org/W3094163702","https://openalex.org/W3096632704","https://openalex.org/W3102457802","https://openalex.org/W3156420330","https://openalex.org/W3173651597","https://openalex.org/W3186197777","https://openalex.org/W3197417694","https://openalex.org/W4210490585","https://openalex.org/W4214717370","https://openalex.org/W4280617872","https://openalex.org/W4283641297","https://openalex.org/W4302561932","https://openalex.org/W4306309318","https://openalex.org/W4313395123","https://openalex.org/W4385438653","https://openalex.org/W4386365945","https://openalex.org/W4400412687","https://openalex.org/W4402289630","https://openalex.org/W4412106701"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2082860237","https://openalex.org/W2119695867","https://openalex.org/W2130076355","https://openalex.org/W1990804418","https://openalex.org/W1993764875","https://openalex.org/W2046158694","https://openalex.org/W2788277189","https://openalex.org/W2013243191","https://openalex.org/W1971568933"],"abstract_inverted_index":{"It":[0],"is":[1,46,70,160,168,172],"well":[2,139],"known":[3,181],"that":[4,16,152,177,202],"evolutionary":[5],"algorithms":[6],"can":[7,145],"benefit":[8],"from":[9],"dynamic":[10,37],"choices":[11,39],"of":[12,29,83,120],"the":[13,26,30,47,55,118,121,185,190,205,212,215],"key":[14],"parameters":[15,109,135],"control":[17,61,87,148,182,200,218],"their":[18,22],"behavior,":[19],"to":[20,25,174,231],"adjust":[21],"search":[23],"strategy":[24],"different":[27],"stages":[28],"optimization":[31],"process.":[32],"A":[33],"prominent":[34],"example":[35],"where":[36],"parameter":[38,60,75,86],"have":[40],"shown":[41],"a":[42,81,161,198],"provable":[43],"super-constant":[44],"speed-up":[45],"(1":[48,122],"+":[49,123],"(\u03bb,":[50,124],"\u03bb))":[51,125],"Genetic":[52,126],"Algorithm":[53,127],"optimizing":[54,128],"OneMax":[56],"function.":[57],"While":[58],"optimal":[59],"policies":[62,105,176,183],"result":[63,78],"in":[64,85,92],"linear":[65],"expected":[66],"running":[67,95],"times,":[68],"this":[69,114,221],"not":[71],"possible":[72],"with":[73],"static":[74],"choices.":[76],"This":[77],"has":[79],"spurred":[80],"lot":[82],"interest":[84],"policies.":[88,149],"However,":[89],"many":[90],"works,":[91,166],"particular":[93],"theoretical":[94],"time":[96],"analyses,":[97],"focus":[98],"on":[99,184,189,220],"controlling":[100,107],"one":[101],"single":[102],"parameter.":[103],"Deriving":[104],"for":[106,225],"multiple":[108],"remains":[110],"very":[111,169],"challenging.":[112],"In":[113],"work,":[115],"we":[116,196],"reconsider":[117],"problem":[119,228],"OneMax.":[129],"We":[130,150],"decouple":[131],"its":[132],"four":[133],"main":[134],"and":[136,171,211],"investigate":[137],"how":[138],"state-of-the-art":[140],"deep":[141,155],"reinforcement":[142,156,194],"learning":[143,157],"techniques":[144],"approximate":[146],"good":[147],"show":[151],"although":[153],"making":[154],"learn":[158],"effectively":[159],"challenging":[162],"task,":[163],"once":[164],"it":[165,167],"powerful":[170],"able":[173],"find":[175],"outperform":[178],"all":[179,226],"previously":[180],"same":[186],"benchmark.":[187],"Based":[188],"results":[191],"found":[192],"through":[193],"learning,":[195],"derive":[197],"simple":[199],"policy":[201,219],"consistently":[203],"outperforms":[204],"default":[206],"theory-recommended":[207],"setting":[208],"by":[209,223],"27%":[210],"irace-tuned":[213],"policy,":[214],"strongest":[216],"existing":[217],"benchmark,":[222],"13%,":[224],"tested":[227],"sizes":[229],"up":[230],"40,000.":[232]},"counts_by_year":[],"updated_date":"2026-06-29T08:53:18.405633","created_date":"2025-10-10T00:00:00"}