{"id":"https://openalex.org/W7129430162","doi":"https://doi.org/10.1016/j.swevo.2026.102330","title":"CMA-MAPPO: Integrating Covariance Matrix Adaptation Evolution Strategy with Multi-Agent Proximal Policy Optimization for enhanced exploration in sparse-reward environments","display_name":"CMA-MAPPO: Integrating Covariance Matrix Adaptation Evolution Strategy with Multi-Agent Proximal Policy Optimization for enhanced exploration in sparse-reward environments","publication_year":2026,"publication_date":"2026-02-17","ids":{"openalex":"https://openalex.org/W7129430162","doi":"https://doi.org/10.1016/j.swevo.2026.102330"},"language":"en","primary_location":{"id":"doi:10.1016/j.swevo.2026.102330","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.swevo.2026.102330","pdf_url":null,"source":{"id":"https://openalex.org/S2764346689","display_name":"Swarm and Evolutionary Computation","issn_l":"2210-6502","issn":["2210-6502","2210-6510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Swarm and Evolutionary Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115875611","display_name":"A.H. Khatami","orcid":null},"institutions":[{"id":"https://openalex.org/I80543232","display_name":"K.N.Toosi University of Technology","ror":"https://ror.org/0433abe34","country_code":"IR","type":"education","lineage":["https://openalex.org/I80543232"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"A.H. Khatami","raw_affiliation_strings":["K. N. Toosi University of Technology, 470 Mirdamad Ave., West, Tehran, 19697, Iran"],"raw_orcid":"https://orcid.org/0009-0006-9045-6635","affiliations":[{"raw_affiliation_string":"K. N. Toosi University of Technology, 470 Mirdamad Ave., West, Tehran, 19697, Iran","institution_ids":["https://openalex.org/I80543232"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5115875611"],"corresponding_institution_ids":["https://openalex.org/I80543232"],"apc_list":{"value":3580,"currency":"USD","value_usd":3580},"apc_paid":null,"fwci":9.2915,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96049447,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"102","issue":null,"first_page":"102330","last_page":"102330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4871000051498413,"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":0.4871000051498413,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.13269999623298645,"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":0.05460000038146973,"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/cma-es","display_name":"CMA-ES","score":0.7468000054359436},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6880000233650208},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6434000134468079},{"id":"https://openalex.org/keywords/differential-evolution","display_name":"Differential evolution","score":0.546999990940094},{"id":"https://openalex.org/keywords/evolution-strategy","display_name":"Evolution strategy","score":0.5052000284194946},{"id":"https://openalex.org/keywords/inner-loop","display_name":"Inner loop","score":0.48420000076293945},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4643999934196472},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4097000062465668},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38420000672340393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8539999723434448},{"id":"https://openalex.org/C205555498","wikidata":"https://www.wikidata.org/wiki/Q505588","display_name":"CMA-ES","level":4,"score":0.7468000054359436},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6880000233650208},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6434000134468079},{"id":"https://openalex.org/C74750220","wikidata":"https://www.wikidata.org/wiki/Q2662197","display_name":"Differential evolution","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C207002847","wikidata":"https://www.wikidata.org/wiki/Q2912857","display_name":"Evolution strategy","level":3,"score":0.5052000284194946},{"id":"https://openalex.org/C58716799","wikidata":"https://www.wikidata.org/wiki/Q6035648","display_name":"Inner loop","level":3,"score":0.48420000076293945},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4643999934196472},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4368000030517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43380001187324524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4287000000476837},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.swevo.2026.102330","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.swevo.2026.102330","pdf_url":null,"source":{"id":"https://openalex.org/S2764346689","display_name":"Swarm and Evolutionary Computation","issn_l":"2210-6502","issn":["2210-6502","2210-6510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Swarm and Evolutionary Computation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1595159159","https://openalex.org/W1641379095","https://openalex.org/W1898867814","https://openalex.org/W1914583973","https://openalex.org/W2112036188","https://openalex.org/W2138537392","https://openalex.org/W2807185344","https://openalex.org/W3131407372","https://openalex.org/W4214963685","https://openalex.org/W4220747123","https://openalex.org/W4285603060","https://openalex.org/W4306786778","https://openalex.org/W4360978881","https://openalex.org/W4366680618","https://openalex.org/W4381149195","https://openalex.org/W4381163735","https://openalex.org/W4391058219","https://openalex.org/W4392298212","https://openalex.org/W4396652121","https://openalex.org/W4400412550","https://openalex.org/W4400956013","https://openalex.org/W4401433010","https://openalex.org/W4401596732","https://openalex.org/W4401657419","https://openalex.org/W4401863443","https://openalex.org/W4404522290","https://openalex.org/W4404877232","https://openalex.org/W4405438107","https://openalex.org/W4409568406","https://openalex.org/W4409594643"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-02-18T00:00:00"}