{"id":"https://openalex.org/W4294811578","doi":"https://doi.org/10.1109/cec55065.2022.9870209","title":"Combining Soft-Actor Critic with Cross-Entropy Method for Policy Search in Continuous Control","display_name":"Combining Soft-Actor Critic with Cross-Entropy Method for Policy Search in Continuous Control","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4294811578","doi":"https://doi.org/10.1109/cec55065.2022.9870209"},"language":"en","primary_location":{"id":"doi:10.1109/cec55065.2022.9870209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec55065.2022.9870209","pdf_url":null,"source":{"id":"https://openalex.org/S4363605353","display_name":"2022 IEEE Congress on Evolutionary Computation (CEC)","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":"2022 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100629902","display_name":"Hieu T. Nguyen","orcid":"https://orcid.org/0000-0003-2392-3492"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hieu Trung Nguyen","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam","Vietnam National University, Ho Chi Minh City, Vietnam","University of Information Technology, Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]},{"raw_affiliation_string":"Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]},{"raw_affiliation_string":"University of Information Technology, Ho Chi Minh City, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029421157","display_name":"Khang Tran","orcid":"https://orcid.org/0000-0001-7250-4863"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Khang Tran","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam","University of Information Technology, Ho Chi Minh City, Vietnam","Vietnam National University, Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]},{"raw_affiliation_string":"University of Information Technology, Ho Chi Minh City, Vietnam","institution_ids":[]},{"raw_affiliation_string":"Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081219326","display_name":"Ngoc Hoang Luong","orcid":"https://orcid.org/0000-0002-6768-1950"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Ngoc Hoang Luong","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam","University of Information Technology, Ho Chi Minh City, Vietnam","Vietnam National University, Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]},{"raw_affiliation_string":"University of Information Technology, Ho Chi Minh City, Vietnam","institution_ids":[]},{"raw_affiliation_string":"Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123565023"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9682000279426575,"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":0.7962194085121155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6863527894020081},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5492756366729736},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4608784019947052},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.452671080827713},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.41508662700653076},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3726356625556946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35415446758270264},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17100927233695984},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1011301577091217}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7962194085121155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6863527894020081},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5492756366729736},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4608784019947052},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.452671080827713},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.41508662700653076},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3726356625556946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35415446758270264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17100927233695984},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1011301577091217},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cec55065.2022.9870209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec55065.2022.9870209","pdf_url":null,"source":{"id":"https://openalex.org/S4363605353","display_name":"2022 IEEE Congress on Evolutionary Computation (CEC)","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":"2022 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1522301498","https://openalex.org/W1577352482","https://openalex.org/W2158782408","https://openalex.org/W2166160300","https://openalex.org/W2596367596","https://openalex.org/W2736601468","https://openalex.org/W2754517384","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2894662639","https://openalex.org/W2951226532","https://openalex.org/W2951799422","https://openalex.org/W2963095800","https://openalex.org/W2963864421","https://openalex.org/W2995617888","https://openalex.org/W2997896361","https://openalex.org/W3044501026","https://openalex.org/W3183892796","https://openalex.org/W4205513846","https://openalex.org/W4232981643","https://openalex.org/W4288418953","https://openalex.org/W4310001898","https://openalex.org/W6631190155","https://openalex.org/W6684921986","https://openalex.org/W6730111887","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6755459763","https://openalex.org/W6755903938","https://openalex.org/W6762760680","https://openalex.org/W6763476460","https://openalex.org/W6771730547","https://openalex.org/W6780559895","https://openalex.org/W6781218111","https://openalex.org/W6795946752","https://openalex.org/W6798240405"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"CEM-SAC":[5],"-":[6],"a":[7,24,115,132],"hybridization":[8],"between":[9],"the":[10,19,32,42,58,67,82,87,108,123,139,143],"cross-entropy":[11],"method":[12,118],"(CEM),":[13],"i.e.,":[14,23],"an":[15],"estimation-of-distribution":[16],"algorithm,":[17,130],"and":[18,86,113,122],"soft-actor":[20],"critic":[21],"(SAC),":[22],"state-of-the-art":[25],"policy":[26,62,93,127],"gradient":[27,63,74,128],"algorithm.":[28],"Our":[29,76],"work":[30],"extends":[31],"evolutionary":[33],"reinforcement":[34,97],"learning":[35,98],"(ERL)":[36],"line":[37],"of":[38,44,61,84,89,96,135,146],"research":[39],"on":[40,131],"integrating":[41],"robustness":[43],"population-based":[45],"stochastic":[46],"black-box":[47],"optimization,":[48],"that":[49,65,119],"typically":[50],"assumes":[51],"little":[52],"to":[53],"no":[54],"problem-specific":[55],"knowledge,":[56],"into":[57],"training":[59,92],"process":[60],"algorithms,":[64],"exploits":[66],"sequential":[68],"decision":[69],"making":[70],"nature":[71],"for":[72,100],"efficient":[73],"estimation.":[75],"hybrid":[77],"approach,":[78],"CEM-SAC,":[79],"exhibits":[80],"both":[81],"stability":[83],"CEM":[85,121],"efficiency":[88],"SAC":[90],"in":[91,138],"neural":[94],"networks":[95],"agents":[99],"solving":[101],"control":[102,136],"problems.":[103],"Experimental":[104],"result":[105],"comparisons":[106],"with":[107],"three":[109],"baselines":[110],"CEM,":[111],"SAC,":[112],"CEM-TD3,":[114],"recently-introduced":[116],"ERL":[117],"combines":[120],"twin-delayed":[124],"deep":[125],"deterministic":[126],"(TD3)":[129],"wide":[133],"range":[134],"tasks":[137],"MuJoCo":[140],"benchmarks":[141],"confirm":[142],"enhanced":[144],"performance":[145],"our":[147],"proposed":[148],"CEM-SAC.":[149],"The":[150],"source":[151],"code":[152],"is":[153],"available":[154],"at":[155],"https://github.com/ELO-Lab/CEM-SAC.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}