{"id":"https://openalex.org/W7127106504","doi":"https://doi.org/10.1007/s44230-026-00135-8","title":"Dynamic Reward-Guided with Multi-Head Attention for Actor-Critic Policy Learning Optimization","display_name":"Dynamic Reward-Guided with Multi-Head Attention for Actor-Critic Policy Learning Optimization","publication_year":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7127106504","doi":"https://doi.org/10.1007/s44230-026-00135-8"},"language":"en","primary_location":{"id":"doi:10.1007/s44230-026-00135-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44230-026-00135-8","pdf_url":null,"source":{"id":"https://openalex.org/S4210207486","display_name":"Human-Centric Intelligent Systems","issn_l":"2667-1336","issn":["2667-1336"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Human-Centric Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1007/s44230-026-00135-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124818770","display_name":"Xiaohui Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Huang","raw_affiliation_strings":["School of Information and Software Engineering, East China Jiaotong University, Nanchang, 330103, Jiangxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, East China Jiaotong University, Nanchang, 330103, Jiangxi Province, China","institution_ids":["https://openalex.org/I13985625"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junhang Zong","orcid":null},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junhang Zong","raw_affiliation_strings":["School of Information and Software Engineering, East China Jiaotong University, Nanchang, 330103, Jiangxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, East China Jiaotong University, Nanchang, 330103, Jiangxi Province, China","institution_ids":["https://openalex.org/I13985625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124833388","display_name":"Xiaofei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Yang","raw_affiliation_strings":["School of Electronic and Communication Engineering, Guangzhou University, Guangzhou, 511370, Guangdong Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Communication Engineering, Guangzhou University, Guangzhou, 511370, Guangdong Province, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124763046","display_name":"Ying Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Yu","raw_affiliation_strings":["School of Information and Software Engineering, East China Jiaotong University, Nanchang, 330103, Jiangxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, East China Jiaotong University, Nanchang, 330103, Jiangxi Province, China","institution_ids":["https://openalex.org/I13985625"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I13985625"],"apc_list":{"value":0,"currency":"USD","value_usd":0},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10241926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"1","first_page":"77","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4180999994277954,"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":0.4180999994277954,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.11159999668598175,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.025100000202655792,"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":0.8450999855995178},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6449000239372253},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.63919997215271},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5626999735832214},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.37470000982284546},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35600000619888306},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.33869999647140503},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.328000009059906}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8450999855995178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573000192642212},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6639000177383423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6496000289916992},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6449000239372253},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.63919997215271},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5626999735832214},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.328000009059906},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.26249998807907104}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44230-026-00135-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44230-026-00135-8","pdf_url":null,"source":{"id":"https://openalex.org/S4210207486","display_name":"Human-Centric Intelligent Systems","issn_l":"2667-1336","issn":["2667-1336"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Human-Centric Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7a2a7e5c54e0481ca23b2c1d894dc510","is_oa":true,"landing_page_url":"https://doaj.org/article/7a2a7e5c54e0481ca23b2c1d894dc510","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Human-Centric Intelligent Systems, Vol 6, Iss 1, Pp 77-92 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44230-026-00135-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44230-026-00135-8","pdf_url":null,"source":{"id":"https://openalex.org/S4210207486","display_name":"Human-Centric Intelligent Systems","issn_l":"2667-1336","issn":["2667-1336"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Human-Centric Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4318879780","display_name":null,"funder_award_id":"20242BAB26023","funder_id":"https://openalex.org/F4320322665","funder_display_name":"Natural Science Foundation of Jiangxi Province"},{"id":"https://openalex.org/G5629859440","display_name":null,"funder_award_id":"62462031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322665","display_name":"Natural Science Foundation of Jiangxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W2145339207","https://openalex.org/W2946794439","https://openalex.org/W2962787969","https://openalex.org/W2973862992","https://openalex.org/W3038822267","https://openalex.org/W3178520484"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"In":[1,87],"offline":[2,44,94,217],"reinforcement":[3,95,127,218],"learning,":[4],"model-based":[5,216],"approaches":[6],"have":[7],"demonstrated":[8],"superior":[9],"data":[10,78,197],"efficiency":[11,198],"by":[12,54,150,220],"leveraging":[13],"learned":[14],"dynamics":[15,72,133,226],"models":[16,33,73],"to":[17,24,36,50,81,83,129,159],"generate":[18],"additional":[19],"training":[20],"samples.":[21],"However,":[22],"due":[23],"inevitable":[25],"model":[26,134,158],"inaccuracies,":[27],"directly":[28],"deriving":[29],"policies":[30],"from":[31],"such":[32],"often":[34],"leads":[35],"suboptimal":[37],"performance":[38],"under":[39,204],"the":[40,43,117,121,157,175],"constraints":[41],"of":[42,120,189],"setting.":[45],"Prior":[46],"work":[47],"has":[48],"attempted":[49],"mitigate":[51],"this":[52,88],"issue":[53],"adopting":[55],"conservative":[56],"strategies":[57],"that":[58,113,179],"avoid":[59],"reliance":[60],"on":[61,76,115,174],"out-of-distribution":[62],"transitions.":[63],"Nevertheless,":[64],"these":[65,151],"methods":[66,185],"still":[67],"face":[68],"notable":[69],"challenges,":[70],"as":[71],"trained":[74],"solely":[75],"historical":[77],"typically":[79],"struggle":[80],"generalize":[82],"unseen":[84],"state-action":[85],"pairs.":[86],"paper,":[89],"we":[90],"propose":[91],"a":[92,110,131,187,211],"novel":[93],"learning":[96,128,219],"method":[97],"Dynamic":[98],"Reward-Guided":[99],"Multi-Head":[100],"Attention":[101],"for":[102,214],"Actor-Critic":[103,141],"Policy":[104],"Learning":[105],"Optimization":[106],"(DRMAAC).":[107],"DRMAAC":[108,180,209],"introduces":[109],"dynamic-aware":[111],"paradigm":[112],"focuses":[114],"capturing":[116],"intrinsic":[118],"characteristics":[119],"behavior":[122],"policy.":[123],"It":[124],"leverages":[125],"inverse":[126],"recover":[130],"reward-consistent":[132,225],"and":[135,164],"identify":[136],"high-return":[137],"states.":[138,153],"Meanwhile,":[139],"an":[140],"architecture":[142],"enhanced":[143],"with":[144,224],"multi-head":[145],"attention":[146,222],"makes":[147],"decisions":[148],"guided":[149],"high-value":[152],"This":[154],"integration":[155],"enables":[156],"better":[160],"capture":[161],"long-term":[162],"dependencies":[163],"prioritize":[165],"informative":[166],"features":[167],"in":[168],"complex":[169],"state":[170],"spaces.":[171],"Empirical":[172],"evaluations":[173],"D4RL":[176],"benchmark":[177],"show":[178],"consistently":[181],"outperforms":[182],"previous":[183],"state-of-the-art":[184],"across":[186],"variety":[188],"tasks.":[190],"These":[191],"results":[192],"highlight":[193],"not":[194],"only":[195],"improved":[196],"but":[199],"also":[200],"strong":[201],"generalization":[202],"capabilities":[203],"diverse":[205],"environmental":[206],"conditions.":[207],"Overall,":[208],"presents":[210],"promising":[212],"direction":[213],"advancing":[215],"combining":[221],"mechanisms":[223],"modeling.":[227]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-02-03T00:00:00"}