{"id":"https://openalex.org/W4412106701","doi":"https://doi.org/10.1145/3712256.3726395","title":"On the Importance of Reward Design in Reinforcement Learning-based Dynamic Algorithm Configuration: A Case Study on OneMax with (1+(\u03bb,\u03bb))-GA","display_name":"On the Importance of Reward Design in Reinforcement Learning-based Dynamic Algorithm Configuration: A Case Study on OneMax with (1+(\u03bb,\u03bb))-GA","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4412106701","doi":"https://doi.org/10.1145/3712256.3726395"},"language":"en","primary_location":{"id":"doi:10.1145/3712256.3726395","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712256.3726395","pdf_url":null,"source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.20265","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/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":["CNRS,LIP6, Sorbonne University, Paris, France","University of St Andrews, St Andrews, United Kingdom","University of St Andrews [Scotland] (St Andrews KY16 9AJ, Fife, Scotland, UK - United Kingdom)"],"raw_orcid":"https://orcid.org/0009-0004-7707-2069","affiliations":[{"raw_affiliation_string":"CNRS,LIP6, Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I39804081"]},{"raw_affiliation_string":"University of St Andrews, St Andrews, United Kingdom","institution_ids":["https://openalex.org/I16835326"]},{"raw_affiliation_string":"University of St Andrews [Scotland] (St Andrews KY16 9AJ, Fife, Scotland, UK - United Kingdom)","institution_ids":["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","University of St Andrews [Scotland] (St Andrews KY16 9AJ, Fife, Scotland, UK - 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"]},{"raw_affiliation_string":"University of St Andrews [Scotland] (St Andrews KY16 9AJ, Fife, Scotland, UK - United Kingdom)","institution_ids":["https://openalex.org/I16835326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059374472","display_name":"Andr\u00e9 Biedenkapp","orcid":"https://orcid.org/0000-0002-8703-8559"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Biedenkapp","raw_affiliation_strings":["University of Freiburg, Freiburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8703-8559","affiliations":[{"raw_affiliation_string":"University of Freiburg, Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"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/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Carola Doerr","raw_affiliation_strings":["CNRS,LIP6, Sorbonne University, Paris, France","CNRS - Centre National de la Recherche Scientifique (France)"],"raw_orcid":"https://orcid.org/0000-0002-4981-3227","affiliations":[{"raw_affiliation_string":"CNRS,LIP6, Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I39804081"]},{"raw_affiliation_string":"CNRS - Centre National de la Recherche Scientifique (France)","institution_ids":["https://openalex.org/I1294671590"]}]},{"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","University of St Andrews [Scotland] (St Andrews KY16 9AJ, Fife, Scotland, UK - 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"]},{"raw_affiliation_string":"University of St Andrews [Scotland] (St Andrews KY16 9AJ, Fife, Scotland, UK - United Kingdom)","institution_ids":["https://openalex.org/I16835326"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6158,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67307692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1162","last_page":"1171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9891999959945679,"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":0.7946428060531616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5349354147911072},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4425595700740814},{"id":"https://openalex.org/keywords/algorithm-design","display_name":"Algorithm design","score":0.43104782700538635},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4014137387275696},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3746351897716522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3330687880516052},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2587852478027344},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1751774251461029}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7946428060531616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5349354147911072},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4425595700740814},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.43104782700538635},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4014137387275696},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3746351897716522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3330687880516052},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2587852478027344},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1751774251461029},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3712256.3726395","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712256.3726395","pdf_url":null,"source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.20265","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.20265","pdf_url":"https://arxiv.org/pdf/2502.20265","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05171390v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05171390","pdf_url":null,"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":"GECCO '25: Genetic and Evolutionary Computation Conference, Jul 2025, Malaga, Spain. pp.1162-1171, ⟨10.1145/3712256.3726395⟩","raw_type":"Conference papers"},{"id":"pmh:oai:freidok.uni-freiburg.de:275281","is_oa":false,"landing_page_url":"https://freidok.uni-freiburg.de/data/275281","pdf_url":null,"source":{"id":"https://openalex.org/S4306401057","display_name":"FreiDok plus (Universit\u00e4tsbibliothek Freiburg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I161046081","host_organization_name":"University of Freiburg","host_organization_lineage":["https://openalex.org/I161046081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference. - New York, NY, USA, 2025. - 1162-1171, ISBN: 979-8-4007-1465-8","raw_type":"article_in_conference_proceedings"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.20265","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.20265","pdf_url":"https://arxiv.org/pdf/2502.20265","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"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/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1130790960","https://openalex.org/W1499408472","https://openalex.org/W1971237725","https://openalex.org/W1992229913","https://openalex.org/W2072441740","https://openalex.org/W2081488245","https://openalex.org/W2110382857","https://openalex.org/W2120297007","https://openalex.org/W2124403132","https://openalex.org/W2141119792","https://openalex.org/W2144744117","https://openalex.org/W2161966552","https://openalex.org/W2499268298","https://openalex.org/W2742595244","https://openalex.org/W2746553466","https://openalex.org/W2766447205","https://openalex.org/W2914782308","https://openalex.org/W2938868012","https://openalex.org/W2955804429","https://openalex.org/W3098022187","https://openalex.org/W3199199693","https://openalex.org/W4210870706","https://openalex.org/W4213377513","https://openalex.org/W4214717370","https://openalex.org/W4221141793","https://openalex.org/W4280617872","https://openalex.org/W4286970057","https://openalex.org/W4304128363","https://openalex.org/W4313395123","https://openalex.org/W4385438653","https://openalex.org/W4401215537","https://openalex.org/W6810565853"],"related_works":["https://openalex.org/W2393888177","https://openalex.org/W2544423928","https://openalex.org/W2117183908","https://openalex.org/W2115794623","https://openalex.org/W4406345323","https://openalex.org/W2067173559","https://openalex.org/W2148738811","https://openalex.org/W1613730747","https://openalex.org/W2541389358","https://openalex.org/W4318948887"],"abstract_inverted_index":{"Dynamic":[0],"Algorithm":[1],"Configuration":[2],"(DAC)":[3],"has":[4],"garnered":[5],"significant":[6],"attention":[7],"in":[8,12,30,55,80,167,183],"recent":[9],"years,":[10],"particularly":[11],"the":[13,26,36,75,81,91,95,111,140,152,155,163,170,178,184],"prevalence":[14],"of":[15,28,63,77,83,94,121,124,142,151,165,180,186,192],"machine":[16],"learning":[17,20,131],"and":[18,130],"deep":[19],"algorithms.":[21],"Numerous":[22],"studies":[23],"have":[24],"leveraged":[25],"robustness":[27],"decision-making":[29],"Reinforcement":[31],"Learning":[32],"(RL)":[33],"to":[34,115,127,147],"address":[35,135],"optimization":[37],"challenges":[38],"associated":[39],"with":[40],"algorithm":[41],"configuration.":[42],"However,":[43],"making":[44],"an":[45,117],"RL":[46,112,156,166,187],"agent":[47],"work":[48,159],"properly":[49],"is":[50],"a":[51,60,86,105,122,143],"non-trivial":[52],"task,":[53],"especially":[54],"reward":[56,78,108,144,181],"design,":[57],"which":[58],"necessitates":[59],"substantial":[61],"amount":[62],"handcrafted":[64],"knowledge":[65],"based":[66],"on":[67,89],"domain":[68],"expertise.":[69],"In":[70],"this":[71],"work,":[72],"we":[73,138],"study":[74,88],"importance":[76],"design":[79],"context":[82],"DAC":[84],"via":[85],"case":[87],"controlling":[90],"population":[92],"size":[93],"(1":[96,171],"+":[97,172],"(\u03bb,":[98,173],"\u03bb))-GA":[99],"optimizing":[100],"OneMax.":[101],"We":[102],"observed":[103],"that":[104],"poorly":[106],"designed":[107],"can":[109],"hinder":[110],"agent's":[113],"ability":[114,164],"learn":[116],"optimal":[118],"policy":[119],"because":[120],"lack":[123],"exploration,":[125],"leading":[126],"both":[128],"scalability":[129,185],"divergence":[132],"issues.":[133],"To":[134],"those":[136],"challenges,":[137],"propose":[139],"application":[141],"shaping":[145,182],"mechanism":[146],"facilitate":[148],"enhanced":[149],"exploration":[150],"environment":[153],"by":[154],"agent.":[157],"Our":[158],"not":[160],"only":[161],"demonstrates":[162],"dynamically":[168],"configuring":[169],"\u03bb))-GA,":[174],"but":[175],"also":[176],"confirms":[177],"advantages":[179],"agents":[188],"across":[189],"various":[190],"sizes":[191],"OneMax":[193],"problems.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}