{"id":"https://openalex.org/W7128634740","doi":"https://doi.org/10.1109/icnsc66229.2025.00019","title":"MCE-ERL:Evolutionary Reinforcement Learning Algorithm with Multi-Distribution Critics Evaluation","display_name":"MCE-ERL:Evolutionary Reinforcement Learning Algorithm with Multi-Distribution Critics Evaluation","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W7128634740","doi":"https://doi.org/10.1109/icnsc66229.2025.00019"},"language":null,"primary_location":{"id":"doi:10.1109/icnsc66229.2025.00019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnsc66229.2025.00019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Networking, Sensing and Control (ICNSC)","raw_type":"proceedings-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/A5006130930","display_name":"Zuohao Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuohao Wu","raw_affiliation_strings":["School of Artificial Intelligence, Chongqing University of Posts and Telecommunications,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Chongqing University of Posts and Telecommunications,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125655745","display_name":"Guang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Li","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences,Chongqing Key Laboratory of Big Data and Intelligent Computing,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences,Chongqing Key Laboratory of Big Data and Intelligent Computing,Chongqing,China","institution_ids":["https://openalex.org/I4210123021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125663269","display_name":"Zihao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107284","display_name":"Chongqing Academy of Science and Technology","ror":"https://ror.org/01gnzp994","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210107284"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Li","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences,Chongqing,China","institution_ids":["https://openalex.org/I4210165038","https://openalex.org/I4210107284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013583240","display_name":"Hongyu Ao","orcid":"https://orcid.org/0000-0003-3684-4195"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Ao","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109774158","display_name":"Mingsheng Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingsheng Shang","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences,Chongqing Key Laboratory of Big Data and Intelligent Computing,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences,Chongqing Key Laboratory of Big Data and Intelligent Computing,Chongqing,China","institution_ids":["https://openalex.org/I4210123021"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81328426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.826200008392334,"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":0.826200008392334,"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":0.10379999876022339,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.016599999740719795,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8784999847412109},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5999000072479248},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5303999781608582},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5148000121116638},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5073999762535095},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.46160000562667847},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.4505000114440918},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4271000027656555}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8784999847412109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6547999978065491},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5999000072479248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.597000002861023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.567799985408783},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5148000121116638},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5073999762535095},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3707999885082245},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.29580000042915344},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C3020157845","wikidata":"https://www.wikidata.org/wiki/Q367359","display_name":"Control sample","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icnsc66229.2025.00019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnsc66229.2025.00019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Networking, Sensing and Control (ICNSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"By":[0],"combining":[1],"gradient-based":[2],"reinforcement":[3,12],"learning":[4,13],"(RL)":[5],"with":[6,63],"gradient-free":[7],"evolutionary":[8,11],"algorithms":[9,15],"(EA),":[10],"(ERL)":[14],"have":[16],"shown":[17],"effectiveness":[18],"in":[19,115],"continuous":[20,94],"high-dimensional":[21],"tasks.":[22],"However,":[23],"traditional":[24],"ERL":[25,61],"faces":[26],"challenges":[27],"such":[28],"as":[29],"distributional":[30],"differences":[31],"between":[32],"EA":[33],"and":[34,46,71,84,103],"RL":[35],"samples":[36],"affecting":[37],"critic":[38],"evaluation,":[39],"limited":[40],"exploration":[41],"due":[42],"to":[43,74,88],"reward-based":[44],"metrics,":[45],"high":[47],"interaction":[48],"costs":[49],"from":[50],"low-quality":[51,90],"samples.":[52,91],"To":[53],"address":[54],"these":[55],"issues,":[56],"we":[57],"propose":[58],"MCE-ERL,":[59],"an":[60],"algorithm":[62],"multi-distribution":[64,72],"critics.":[65],"We":[66],"uses":[67],"a":[68],"value":[69],"group":[70],"sampling":[73,87],"better":[75,104],"cover":[76],"the":[77],"sample":[78,112],"space,":[79],"leverages":[80],"uncertainty":[81],"for":[82,110],"exploration,":[83],"applies":[85],"importance":[86],"filter":[89],"Experiments":[92],"on":[93],"control":[95],"tasks":[96],"show":[97],"that":[98],"MCE-ERL":[99],"achieves":[100],"faster":[101],"convergence":[102],"performance":[105],"than":[106],"baselines,":[107],"offering":[108],"insights":[109],"reducing":[111],"collection":[113],"loss":[114],"real-world":[116],"robotic":[117],"applications.":[118]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-12T00:00:00"}