{"id":"https://openalex.org/W4367727829","doi":"https://doi.org/10.1109/tnnls.2023.3264540","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","display_name":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","publication_year":2023,"publication_date":"2023-05-02","ids":{"openalex":"https://openalex.org/W4367727829","doi":"https://doi.org/10.1109/tnnls.2023.3264540","pmid":"https://pubmed.ncbi.nlm.nih.gov/37130255"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3264540","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3264540","pdf_url":"https://ieeexplore.ieee.org/ielx7/5962385/6104215/10114063.pdf","source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/5962385/6104215/10114063.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086524604","display_name":"Amjad Yousef Majid","orcid":"https://orcid.org/0000-0001-8225-6410"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Amjad Yousef Majid","raw_affiliation_strings":["Department of Microelectronics, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-8225-6410","affiliations":[{"raw_affiliation_string":"Department of Microelectronics, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060249919","display_name":"Serge Saaybi","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Serge Saaybi","raw_affiliation_strings":["Department of Software Technology, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Technology, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015166903","display_name":"Vincent Fran\u00e7ois-Lavet","orcid":"https://orcid.org/0000-0002-8593-9740"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Vincent Francois-Lavet","raw_affiliation_strings":["Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045465417","display_name":"Ramjee Prasad","orcid":"https://orcid.org/0000-0001-7443-7641"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"R. Venkatesha Prasad","raw_affiliation_strings":["Department of Software Technology, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-7443-7641","affiliations":[{"raw_affiliation_string":"Department of Software Technology, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016756609","display_name":"C.J.M. Verhoeven","orcid":"https://orcid.org/0000-0002-0106-8117"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Chris Verhoeven","raw_affiliation_strings":["Department of Microelectronics, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-0106-8117","affiliations":[{"raw_affiliation_string":"Department of Microelectronics, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.4827,"has_fulltext":true,"cited_by_count":79,"citation_normalized_percentile":{"value":0.99016753,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"35","issue":"9","first_page":"11939","last_page":"11957"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9986000061035156,"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":0.992900013923645,"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":0.8213450312614441},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6331903338432312},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.620222270488739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5743409395217896},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5057830810546875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47098633646965027},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.46465176343917847},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.339740127325058},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09388148784637451},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.06573790311813354}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8213450312614441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6331903338432312},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.620222270488739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5743409395217896},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5057830810546875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47098633646965027},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.46465176343917847},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.339740127325058},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09388148784637451},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.06573790311813354},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tnnls.2023.3264540","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3264540","pdf_url":"https://ieeexplore.ieee.org/ielx7/5962385/6104215/10114063.pdf","source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37130255","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37130255","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:research.vu.nl:openaire/fa03b103-3561-48fe-b2e7-789e4992c6e6","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/fa03b103-3561-48fe-b2e7-789e4992c6e6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Majid, A Y, Saaybi, S, Francois-Lavet, V, Prasad, R V & Verhoeven, C 2024, 'Deep Reinforcement Learning Versus Evolution Strategies : A Comparative Survey', IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 9, pp. 11939-11957. https://doi.org/10.1109/TNNLS.2023.3264540","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:research.vu.nl:publications/fa03b103-3561-48fe-b2e7-789e4992c6e6","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/fa03b103-3561-48fe-b2e7-789e4992c6e6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Majid, A Y, Saaybi, S, Francois-Lavet, V, Prasad, R V & Verhoeven, C 2024, 'Deep Reinforcement Learning Versus Evolution Strategies : A Comparative Survey', IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 9, pp. 11939-11957. https://doi.org/10.1109/TNNLS.2023.3264540","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/tnnls.2023.3264540","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3264540","pdf_url":"https://ieeexplore.ieee.org/ielx7/5962385/6104215/10114063.pdf","source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Neural Networks and Learning Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367727829.pdf","grobid_xml":"https://content.openalex.org/works/W4367727829.grobid-xml"},"referenced_works_count":196,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W50090763","https://openalex.org/W103885025","https://openalex.org/W135283623","https://openalex.org/W288089086","https://openalex.org/W1503196123","https://openalex.org/W1512383952","https://openalex.org/W1514875444","https://openalex.org/W1547737196","https://openalex.org/W1569918514","https://openalex.org/W1583380718","https://openalex.org/W1595483645","https://openalex.org/W1607316222","https://openalex.org/W1641379095","https://openalex.org/W1966456942","https://openalex.org/W1980035368","https://openalex.org/W1988210060","https://openalex.org/W1991944685","https://openalex.org/W1994286308","https://openalex.org/W2025406794","https://openalex.org/W2034806191","https://openalex.org/W2056354534","https://openalex.org/W2059654640","https://openalex.org/W2066251678","https://openalex.org/W2101677491","https://openalex.org/W2107544712","https://openalex.org/W2112036188","https://openalex.org/W2119717200","https://openalex.org/W2126222949","https://openalex.org/W2130990842","https://openalex.org/W2137825550","https://openalex.org/W2138537392","https://openalex.org/W2145339207","https://openalex.org/W2168405694","https://openalex.org/W2194966727","https://openalex.org/W2462548332","https://openalex.org/W2478397249","https://openalex.org/W2482817076","https://openalex.org/W2575705757","https://openalex.org/W2588283865","https://openalex.org/W2617547828","https://openalex.org/W2768629321","https://openalex.org/W2778749116","https://openalex.org/W2794711922","https://openalex.org/W2810602713","https://openalex.org/W2892258706","https://openalex.org/W2893147122","https://openalex.org/W2904998808","https://openalex.org/W2913845934","https://openalex.org/W2921955147","https://openalex.org/W2938321354","https://openalex.org/W2955616331","https://openalex.org/W2956256673","https://openalex.org/W2963184939","https://openalex.org/W2963523627","https://openalex.org/W2963658727","https://openalex.org/W2963900541","https://openalex.org/W2964025389","https://openalex.org/W2964241534","https://openalex.org/W2964299732","https://openalex.org/W2965185450","https://openalex.org/W2968817375","https://openalex.org/W2981038142","https://openalex.org/W2983178256","https://openalex.org/W2997289589","https://openalex.org/W3007384386","https://openalex.org/W3012109984","https://openalex.org/W3016550207","https://openalex.org/W3023368031","https://openalex.org/W3033405336","https://openalex.org/W3034606848","https://openalex.org/W3040652553","https://openalex.org/W3040707741","https://openalex.org/W3041398791","https://openalex.org/W3090612618","https://openalex.org/W3091795298","https://openalex.org/W3092053846","https://openalex.org/W3095315965","https://openalex.org/W3099518626","https://openalex.org/W3100366369","https://openalex.org/W3103635569","https://openalex.org/W3106649810","https://openalex.org/W3114601207","https://openalex.org/W3120070300","https://openalex.org/W3127770912","https://openalex.org/W3129853634","https://openalex.org/W3130568950","https://openalex.org/W3134329363","https://openalex.org/W3136541425","https://openalex.org/W3139377883","https://openalex.org/W3153216919","https://openalex.org/W3154934604","https://openalex.org/W3186352882","https://openalex.org/W3197491224","https://openalex.org/W3198249268","https://openalex.org/W3200056662","https://openalex.org/W3203069471","https://openalex.org/W4220744913","https://openalex.org/W4220747123","https://openalex.org/W4247067162","https://openalex.org/W4254547512","https://openalex.org/W4256520039","https://openalex.org/W6628294491","https://openalex.org/W6633472260","https://openalex.org/W6635465357","https://openalex.org/W6636881020","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6645563480","https://openalex.org/W6677939520","https://openalex.org/W6682262322","https://openalex.org/W6683204974","https://openalex.org/W6684859321","https://openalex.org/W6684921986","https://openalex.org/W6692055482","https://openalex.org/W6692846177","https://openalex.org/W6695011786","https://openalex.org/W6702989015","https://openalex.org/W6713411898","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6718379498","https://openalex.org/W6720057410","https://openalex.org/W6729433768","https://openalex.org/W6730641667","https://openalex.org/W6731982132","https://openalex.org/W6734097942","https://openalex.org/W6734678876","https://openalex.org/W6735033012","https://openalex.org/W6735579001","https://openalex.org/W6735641298","https://openalex.org/W6736057607","https://openalex.org/W6737069938","https://openalex.org/W6738174457","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6740222838","https://openalex.org/W6740422405","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6741408367","https://openalex.org/W6742529797","https://openalex.org/W6745120743","https://openalex.org/W6745497480","https://openalex.org/W6747092830","https://openalex.org/W6747943641","https://openalex.org/W6748317118","https://openalex.org/W6748554570","https://openalex.org/W6748600884","https://openalex.org/W6748603076","https://openalex.org/W6748638692","https://openalex.org/W6748839928","https://openalex.org/W6749032143","https://openalex.org/W6749304979","https://openalex.org/W6750254146","https://openalex.org/W6750322874","https://openalex.org/W6751357015","https://openalex.org/W6753807341","https://openalex.org/W6754957883","https://openalex.org/W6755459763","https://openalex.org/W6755555326","https://openalex.org/W6756192075","https://openalex.org/W6756303580","https://openalex.org/W6756463683","https://openalex.org/W6757096465","https://openalex.org/W6757184387","https://openalex.org/W6758419613","https://openalex.org/W6758641611","https://openalex.org/W6758978475","https://openalex.org/W6761831921","https://openalex.org/W6762760680","https://openalex.org/W6762863188","https://openalex.org/W6763476460","https://openalex.org/W6764724164","https://openalex.org/W6764943343","https://openalex.org/W6768397756","https://openalex.org/W6768560635","https://openalex.org/W6768827935","https://openalex.org/W6768842719","https://openalex.org/W6769580333","https://openalex.org/W6770360514","https://openalex.org/W6771807793","https://openalex.org/W6775522024","https://openalex.org/W6776331362","https://openalex.org/W6784996202","https://openalex.org/W6786207720","https://openalex.org/W6786364697","https://openalex.org/W6789460321","https://openalex.org/W6789771441","https://openalex.org/W6792155000","https://openalex.org/W6809958980","https://openalex.org/W6810137820","https://openalex.org/W6839132455","https://openalex.org/W6846392434","https://openalex.org/W6863903970","https://openalex.org/W7062612498"],"related_works":["https://openalex.org/W4295769391","https://openalex.org/W2972220648","https://openalex.org/W2332667808","https://openalex.org/W1997921863","https://openalex.org/W3112960490","https://openalex.org/W4306904969","https://openalex.org/W93605524","https://openalex.org/W2021145421","https://openalex.org/W821271700","https://openalex.org/W2138720691"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,87],"(DRL)":[3],"and":[4,29,41,50,67,86,99],"evolution":[5],"strategies":[6],"(ESs)":[7],"have":[8],"surpassed":[9],"human-level":[10],"control":[11],"in":[12],"many":[13,18],"sequential":[14],"decision-making":[15],"problems,":[16],"yet":[17],"open":[19],"challenges":[20,72],"still":[21],"exist.":[22],"To":[23],"get":[24],"insights":[25],"into":[26],"the":[27,91],"strengths":[28],"weaknesses":[30],"of":[31,37,93],"DRL":[32,98],"versus":[33,80],"ESs,":[34],"an":[35],"analysis":[36],"their":[38,47],"respective":[39],"capabilities":[40],"limitations":[42],"is":[43,54],"provided.":[44],"After":[45],"presenting":[46],"fundamental":[48],"concepts":[49],"algorithms,":[51],"a":[52],"comparison":[53],"provided":[55],"on":[56],"key":[57],"aspects,":[58],"such":[59],"as":[60],"scalability,":[61],"exploration,":[62],"adaptation":[63],"to":[64,88],"dynamic":[65],"environments,":[66],"multiagent":[68],"learning.":[69],"Current":[70],"research":[71],"are":[73,101],"also":[74],"discussed,":[75],"including":[76],"sample":[77],"efficiency,":[78],"exploration":[79],"exploitation,":[81],"dealing":[82],"with":[83],"sparse":[84],"rewards,":[85],"plan.":[89],"Then,":[90],"benefits":[92],"hybrid":[94],"algorithms":[95],"that":[96],"combine":[97],"ESs":[100],"highlighted.":[102]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}