{"id":"https://openalex.org/W4296363463","doi":"https://doi.org/10.1017/s0269888922000042","title":"A scalable species-based genetic algorithm for reinforcement learning problems","display_name":"A scalable species-based genetic algorithm for reinforcement learning problems","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4296363463","doi":"https://doi.org/10.1017/s0269888922000042"},"language":"en","primary_location":{"id":"doi:10.1017/s0269888922000042","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s0269888922000042","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/F81D312989BA030713E7CC2E87D20AC7/S0269888922000042a.pdf/div-class-title-a-scalable-species-based-genetic-algorithm-for-reinforcement-learning-problems-div.pdf","source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/F81D312989BA030713E7CC2E87D20AC7/S0269888922000042a.pdf/div-class-title-a-scalable-species-based-genetic-algorithm-for-reinforcement-learning-problems-div.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061024236","display_name":"Anirudh Seth","orcid":"https://orcid.org/0000-0003-3762-2578"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]},{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Anirudh Seth","raw_affiliation_strings":["Ericsson, Torshamnsgatan 23, Stockholm 164 83, Sweden;","KTH, Brinellvgen 8, Stockholm 114 28, Sweden;","KTH, Brinellv\u00e4gen 8, Stockholm 114 28, Sweden","E-mails:","E-mail:","Ericsson, Torshamnsgatan 23, Stockholm 164 83, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-3762-2578","affiliations":[{"raw_affiliation_string":"Ericsson, Torshamnsgatan 23, Stockholm 164 83, Sweden;","institution_ids":["https://openalex.org/I1306339040"]},{"raw_affiliation_string":"KTH, Brinellvgen 8, Stockholm 114 28, Sweden;","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH, Brinellv\u00e4gen 8, Stockholm 114 28, Sweden","institution_ids":[]},{"raw_affiliation_string":"E-mails:","institution_ids":[]},{"raw_affiliation_string":"E-mail:","institution_ids":[]},{"raw_affiliation_string":"Ericsson, Torshamnsgatan 23, Stockholm 164 83, Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005176879","display_name":"Alexandros Nikou","orcid":"https://orcid.org/0000-0002-8696-1536"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Alexandros Nikou","raw_affiliation_strings":["Ericsson, Torshamnsgatan 23, Stockholm 164 83, Sweden;","Ericsson, Torshamnsgatan 23, Stockholm 164 83, Sweden","E-mails:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ericsson, Torshamnsgatan 23, Stockholm 164 83, Sweden;","institution_ids":["https://openalex.org/I1306339040"]},{"raw_affiliation_string":"Ericsson, Torshamnsgatan 23, Stockholm 164 83, Sweden","institution_ids":["https://openalex.org/I1306339040"]},{"raw_affiliation_string":"E-mails:","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011170113","display_name":"Marios Daoutis","orcid":"https://orcid.org/0000-0003-0401-6897"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Marios Daoutis","raw_affiliation_strings":["Ericsson, Torshamnsgatan 23, Stockholm 164 83, Sweden;","E-mails:","Ericsson, Torshamnsgatan 23, Stockholm 164 83, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-0401-6897","affiliations":[{"raw_affiliation_string":"Ericsson, Torshamnsgatan 23, Stockholm 164 83, Sweden;","institution_ids":["https://openalex.org/I1306339040"]},{"raw_affiliation_string":"E-mails:","institution_ids":[]},{"raw_affiliation_string":"Ericsson, Torshamnsgatan 23, Stockholm 164 83, Sweden","institution_ids":["https://openalex.org/I1306339040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061024236"],"corresponding_institution_ids":["https://openalex.org/I1306339040","https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.4162,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68495354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"37","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9994000196456909,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9994000196456909,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9973000288009644,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.98580002784729,"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":0.7459779977798462},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7447576522827148},{"id":"https://openalex.org/keywords/crossover","display_name":"Crossover","score":0.5559494495391846},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5024948120117188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4706506133079529},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4699796736240387},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.44708001613616943},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.4184766411781311},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.41677093505859375},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37913569808006287},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36440420150756836},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3605760931968689},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11914783716201782}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7459779977798462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7447576522827148},{"id":"https://openalex.org/C122507166","wikidata":"https://www.wikidata.org/wiki/Q628906","display_name":"Crossover","level":2,"score":0.5559494495391846},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5024948120117188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4706506133079529},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4699796736240387},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.44708001613616943},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.4184766411781311},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41677093505859375},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37913569808006287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36440420150756836},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3605760931968689},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11914783716201782},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s0269888922000042","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s0269888922000042","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/F81D312989BA030713E7CC2E87D20AC7/S0269888922000042a.pdf/div-class-title-a-scalable-species-based-genetic-algorithm-for-reinforcement-learning-problems-div.pdf","source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1017/s0269888922000042","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s0269888922000042","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/F81D312989BA030713E7CC2E87D20AC7/S0269888922000042a.pdf/div-class-title-a-scalable-species-based-genetic-algorithm-for-reinforcement-learning-problems-div.pdf","source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.4300000071525574,"display_name":"No poverty"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320273","display_name":"University of Cambridge","ror":"https://ror.org/013meh722"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296363463.pdf","grobid_xml":"https://content.openalex.org/works/W4296363463.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W755046805","https://openalex.org/W1023926841","https://openalex.org/W1533861849","https://openalex.org/W1659842140","https://openalex.org/W1677182931","https://openalex.org/W1738827650","https://openalex.org/W1965555277","https://openalex.org/W1980516134","https://openalex.org/W1986813169","https://openalex.org/W1994616650","https://openalex.org/W1996076394","https://openalex.org/W2005926822","https://openalex.org/W2020399841","https://openalex.org/W2055496638","https://openalex.org/W2061504687","https://openalex.org/W2064675550","https://openalex.org/W2087617385","https://openalex.org/W2095705004","https://openalex.org/W2097571405","https://openalex.org/W2103496339","https://openalex.org/W2111935653","https://openalex.org/W2119814172","https://openalex.org/W2132211083","https://openalex.org/W2142441581","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2150871235","https://openalex.org/W2151661095","https://openalex.org/W2154022540","https://openalex.org/W2162036626","https://openalex.org/W2164866963","https://openalex.org/W2166160300","https://openalex.org/W2169209873","https://openalex.org/W2173564293","https://openalex.org/W2174817438","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2307253082","https://openalex.org/W2334782222","https://openalex.org/W2462548332","https://openalex.org/W2555780822","https://openalex.org/W2590282505","https://openalex.org/W2596585349","https://openalex.org/W2612306626","https://openalex.org/W2746553466","https://openalex.org/W2779977383","https://openalex.org/W2787933113","https://openalex.org/W2799117832","https://openalex.org/W2877093712","https://openalex.org/W2884642541","https://openalex.org/W2898035736","https://openalex.org/W2920179928","https://openalex.org/W2929287013","https://openalex.org/W2931364255","https://openalex.org/W2935381027","https://openalex.org/W2953212265","https://openalex.org/W2963809228","https://openalex.org/W2964199361","https://openalex.org/W3093649854","https://openalex.org/W3096654951","https://openalex.org/W3161963243","https://openalex.org/W4206215385","https://openalex.org/W4250503569","https://openalex.org/W4299541734","https://openalex.org/W6631943919","https://openalex.org/W6674330103","https://openalex.org/W6682262322","https://openalex.org/W6685331716"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W2140186469","https://openalex.org/W3176564347","https://openalex.org/W4390421286","https://openalex.org/W1985458517","https://openalex.org/W2347477706","https://openalex.org/W2355833770","https://openalex.org/W4299389082","https://openalex.org/W1943663474","https://openalex.org/W4281847915"],"abstract_inverted_index":{"Abstract":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"methods":[4],"often":[5],"rely":[6],"on":[7,132],"gradient":[8],"estimates":[9],"to":[10,36,54,123,168,181],"learn":[11],"an":[12,120],"optimal":[13],"policy":[14],"for":[15,60,101],"control":[16],"problems.":[17,62],"These":[18],"expensive":[19],"computations":[20],"result":[21],"in":[22,189],"long":[23],"training":[24],"times,":[25],"a":[26,40,51,56,74,84,91,108,182],"poor":[27],"rate":[28],"of":[29,70,77,93,107],"convergence,":[30],"and":[31,43,72,89,127,151,158],"sample":[32],"inefficiency":[33],"when":[34,179],"applied":[35,180],"real-world":[37],"problems":[38],"with":[39,139],"large":[41],"state":[42],"action":[44],"space.":[45],"Evolutionary":[46],"Computation":[47],"(EC)-based":[48],"techniques":[49],"offer":[50],"gradient-free":[52,152],"apparatus":[53],"train":[55],"deep":[57,94],"neural":[58,95,109],"network":[59,110],"RL":[61,103],"In":[63],"this":[64],"work,":[65],"we":[66],"leverage":[67],"the":[68,99,102,190],"benefits":[69],"EC":[71],"propose":[73],"novel":[75],"variant":[76],"genetic":[78],"algorithm":[79,171],"called":[80],"SP-GA":[81],"which":[82,118],"utilizes":[83,112],"species-inspired":[85],"weight":[86],"initialization":[87],"strategy":[88],"trains":[90],"population":[92],"networks,":[96],"each":[97],"estimating":[98],"Q-function":[100],"problem.":[104],"Efficient":[105],"encoding":[106],"that":[111],"less":[113],"memory":[114],"is":[115],"also":[116,172],"proposed":[117],"provides":[119],"intuitive":[121],"mechanism":[122],"apply":[124],"Gaussian":[125],"mutations":[126],"single-point":[128],"crossover.":[129],"The":[130,170],"results":[131],"Atari":[133],"2600":[134],"games":[135],"outline":[136],"comparable":[137],"performance":[138],"gradient-based":[140],"algorithms":[141,153],"like":[142,154],"Deep":[143],"Q-Network":[144],"(DQN),":[145],"Asynchronous":[146],"Advantage":[147],"Actor":[148],"Critic":[149],"(A3C),":[150],"Evolution":[155],"Strategy":[156],"(ES)":[157],"simple":[159],"Genetic":[160],"Algorithm":[161],"(GA)":[162],"while":[163],"requiring":[164],"far":[165],"fewer":[166],"hyperparameters":[167],"train.":[169],"improved":[173],"certain":[174],"Key":[175],"Performance":[176],"Indicators":[177],"(KPIs)":[178],"Remote":[183],"Electrical":[184],"Tilt":[185],"(RET)":[186],"optimization":[187],"task":[188],"telecommunication":[191],"domain.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-01-08T20:05:33.558190","created_date":"2025-10-10T00:00:00"}