{"id":"https://openalex.org/W7124918203","doi":"https://doi.org/10.1002/cpe.70555","title":"MSSEAC: Multi\u2010State Soft Elastic Actor\u2010Critic","display_name":"MSSEAC: Multi\u2010State Soft Elastic Actor\u2010Critic","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124918203","doi":"https://doi.org/10.1002/cpe.70555"},"language":"en","primary_location":{"id":"doi:10.1002/cpe.70555","is_oa":false,"landing_page_url":"https://doi.org/10.1002/cpe.70555","pdf_url":null,"source":{"id":"https://openalex.org/S11065456","display_name":"Concurrency and Computation Practice and Experience","issn_l":"1532-0626","issn":["1532-0626","1532-0634"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency and Computation: Practice and Experience","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/A5054698912","display_name":"Yuwan Gu","orcid":"https://orcid.org/0000-0002-3148-9414"},"institutions":[{"id":"https://openalex.org/I4210153482","display_name":"Changzhou University","ror":"https://ror.org/04ymgwq66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210153482"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuwan Gu","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence Changzhou University  Changzhou China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence Changzhou University  Changzhou China","institution_ids":["https://openalex.org/I4210153482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123376109","display_name":"Jie Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153482","display_name":"Changzhou University","ror":"https://ror.org/04ymgwq66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210153482"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Hao","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence Changzhou University  Changzhou China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence Changzhou University  Changzhou China","institution_ids":["https://openalex.org/I4210153482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123400647","display_name":"Fang Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153482","display_name":"Changzhou University","ror":"https://ror.org/04ymgwq66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210153482"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Meng","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence Changzhou University  Changzhou China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence Changzhou University  Changzhou China","institution_ids":["https://openalex.org/I4210153482"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153482","display_name":"Changzhou University","ror":"https://ror.org/04ymgwq66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210153482"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Chen","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence Changzhou University  Changzhou China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence Changzhou University  Changzhou China","institution_ids":["https://openalex.org/I4210153482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123389235","display_name":"Ronghai Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153482","display_name":"Changzhou University","ror":"https://ror.org/04ymgwq66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210153482"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghai Miao","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence Changzhou University  Changzhou China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence Changzhou University  Changzhou China","institution_ids":["https://openalex.org/I4210153482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123371977","display_name":"Jidong Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153482","display_name":"Changzhou University","ror":"https://ror.org/04ymgwq66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210153482"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jidong Lv","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence Changzhou University  Changzhou China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence Changzhou University  Changzhou China","institution_ids":["https://openalex.org/I4210153482"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5054698912"],"corresponding_institution_ids":["https://openalex.org/I4210153482"],"apc_list":{"value":4740,"currency":"USD","value_usd":4740},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07754773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3887999951839447,"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":0.3887999951839447,"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/T10603","display_name":"Smart Grid Energy Management","score":0.16359999775886536,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.1462000012397766,"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":0.7742999792098999},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6057000160217285},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5354999899864197},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5019999742507935},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49540001153945923},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.3921000063419342},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.38909998536109924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8485999703407288},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7742999792098999},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6057000160217285},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5354999899864197},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5019999742507935},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49540001153945923},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3912000060081482},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C2777480716","wikidata":"https://www.wikidata.org/wiki/Q23582796","display_name":"Resource consumption","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.290800005197525},{"id":"https://openalex.org/C30772137","wikidata":"https://www.wikidata.org/wiki/Q5164762","display_name":"Consumption (sociology)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25589999556541443},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/cpe.70555","is_oa":false,"landing_page_url":"https://doi.org/10.1002/cpe.70555","pdf_url":null,"source":{"id":"https://openalex.org/S11065456","display_name":"Concurrency and Computation Practice and Experience","issn_l":"1532-0626","issn":["1532-0626","1532-0634"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency and Computation: Practice and Experience","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7538303197","display_name":null,"funder_award_id":"61906021","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G760930791","display_name":null,"funder_award_id":"CX(22)3104","funder_id":"https://openalex.org/F4320309870","funder_display_name":"Jiangsu Agricultural Science and Technology Innovation Fund"}],"funders":[{"id":"https://openalex.org/F4320309870","display_name":"Jiangsu Agricultural Science and Technology Innovation Fund","ror":"https://ror.org/0335n2618"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1985235885","https://openalex.org/W2775482448","https://openalex.org/W3175254947","https://openalex.org/W3210169707","https://openalex.org/W4213377513","https://openalex.org/W4379739787","https://openalex.org/W4390985631","https://openalex.org/W4392015292","https://openalex.org/W4415800724","https://openalex.org/W7103752298"],"related_works":[],"abstract_inverted_index":{"ABSTRACT":[0],"In":[1],"reinforcement":[2],"learning":[3,27,115],"(RL),":[4],"the":[5,37,49,59,80,90,114,140],"assumption":[6],"of":[7,92,152],"fixed":[8],"control":[9,68,76],"frequency":[10,77],"often":[11],"leads":[12],"to":[13,44,65,88,112,125,131],"computational":[14],"resource":[15],"wastage":[16],"and":[17,57,70],"degraded":[18],"policy":[19],"performance,":[20],"while":[21],"traditional":[22],"single\u2010step":[23,94,146],"temporal":[24,53,82],"difference":[25,83],"(TD)":[26],"suffers":[28],"from":[29,155],"accumulated":[30],"state\u2010value":[31],"estimation":[32,133,137],"bias.":[33],"This":[34],"paper":[35,50],"proposes":[36],"multi\u2010state":[38,81],"soft":[39],"elastic":[40],"actor\u2010critic":[41],"(MSSEAC)":[42],"algorithm":[43],"address":[45,89],"these":[46],"issues:":[47],"First,":[48],"introduces":[51],"a":[52,122],"consumption":[54,72],"penalty":[55],"mechanism":[56],"reconstructs":[58],"actor":[60],"network's":[61],"dual\u2010branch":[62],"output":[63],"structure":[64],"simultaneously":[66],"generate":[67],"actions":[69,109,127],"time":[71],"estimates,":[73],"enabling":[74],"autonomous":[75],"adjustment.":[78],"Second,":[79],"(MSTD)":[84],"framework":[85],"is":[86,105,160],"developed":[87],"limitations":[91],"conventional":[93],"TD":[95,147],"learning.":[96],"Specifically,":[97],"an":[98],"innovative":[99],"experience":[100],"replay":[101],"buffer":[102],"management":[103],"strategy":[104],"proposed,":[106],"where":[107],"historical":[108],"are":[110],"utilized":[111],"stabilize":[113],"process":[116],"during":[117],"initial":[118],"training":[119],"phases,":[120],"with":[121],"gradual":[123],"transition":[124],"policy\u2010generated":[126],"in":[128,145],"later":[129],"stages":[130],"enhance":[132],"accuracy.":[134],"The":[135],"multi\u2010state\u2010value":[136],"effectively":[138],"mitigates":[139],"bias":[141],"accumulation":[142],"problem":[143],"inherent":[144],"methods":[148],"through":[149],"weighted":[150],"fusion":[151],"return":[153],"distributions":[154],"multiple":[156],"future":[157],"states.":[158],"Code":[159],"available":[161],"at:":[162],"https://github.com/asdwqqqq/MSSEAC.git":[163],".":[164]},"counts_by_year":[],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2026-01-21T00:00:00"}
