{"id":"https://openalex.org/W7162697879","doi":"https://doi.org/10.1109/access.2026.3697752","title":"Model Free Adaptive Q-Learning for Stochastic Differential Games With State-Dependent Perturbations and Input Saturation","display_name":"Model Free Adaptive Q-Learning for Stochastic Differential Games With State-Dependent Perturbations and Input Saturation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7162697879","doi":"https://doi.org/10.1109/access.2026.3697752"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3697752","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3697752","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3697752","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038920344","display_name":"Zhifu Jia","orcid":"https://orcid.org/0000-0001-8287-3208"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifu Jia","raw_affiliation_strings":["School of Mathematics and Physics, Suqian University, Suqian, China"],"raw_orcid":"https://orcid.org/0000-0001-8287-3208","affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics, Suqian University, Suqian, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112120445","display_name":"Xie Na","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Xie","raw_affiliation_strings":["School of Mathematics and Physics, Suqian University, Suqian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics, Suqian University, Suqian, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69624969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"82823","last_page":"82835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.5170000195503235,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.5170000195503235,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3824999928474426,"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/T11031","display_name":"Game Theory and Applications","score":0.019700000062584877,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5012000203132629},{"id":"https://openalex.org/keywords/saturation","display_name":"Saturation (graph theory)","score":0.48179998993873596},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.4147999882698059},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.3953000009059906},{"id":"https://openalex.org/keywords/stochastic-differential-equation","display_name":"Stochastic differential equation","score":0.3734999895095825},{"id":"https://openalex.org/keywords/differential-game","display_name":"Differential game","score":0.3084000051021576}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5012000203132629},{"id":"https://openalex.org/C9930424","wikidata":"https://www.wikidata.org/wiki/Q7426587","display_name":"Saturation (graph theory)","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40860000252723694},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3993000090122223},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3691999912261963},{"id":"https://openalex.org/C2779006483","wikidata":"https://www.wikidata.org/wiki/Q1973196","display_name":"Differential game","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.30399999022483826},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C207658827","wikidata":"https://www.wikidata.org/wiki/Q1999781","display_name":"Stochastic resonance","level":4,"score":0.27720001339912415},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3697752","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3697752","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:254cb9a8ea054650ab3ed88fa0391de4","is_oa":true,"landing_page_url":"https://doaj.org/article/254cb9a8ea054650ab3ed88fa0391de4","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":"IEEE Access, Vol 14, Pp 82823-82835 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3697752","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3697752","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.6245471239089966,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G3751028398","display_name":null,"funder_award_id":"Z2025039","funder_id":"https://openalex.org/F4320336657","funder_display_name":"Xuzhou Science and Technology Program"},{"id":"https://openalex.org/G5377628348","display_name":null,"funder_award_id":"25KJD110004","funder_id":"https://openalex.org/F4320335440","funder_display_name":"Natural Science Research of Jiangsu Higher Education Institutions of China"},{"id":"https://openalex.org/G5556619252","display_name":null,"funder_award_id":"K202440","funder_id":"https://openalex.org/F4320336657","funder_display_name":"Xuzhou Science and Technology Program"},{"id":"https://openalex.org/G8314593953","display_name":null,"funder_award_id":"K202506","funder_id":"https://openalex.org/F4320336657","funder_display_name":"Xuzhou Science and Technology Program"}],"funders":[{"id":"https://openalex.org/F4320335440","display_name":"Natural Science Research of Jiangsu Higher Education Institutions of China","ror":null},{"id":"https://openalex.org/F4320336657","display_name":"Xuzhou Science and Technology Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"online":[4],"adaptive":[5,69],"Q-learning":[6,158],"algorithm":[7,155],"for":[8,32,61],"linear-quadratic":[9],"nonzero-sum":[10],"stochastic":[11,43,98],"differential":[12],"games":[13],"with":[14,134],"completely":[15],"unknown":[16],"system":[17,116],"dynamics,":[18],"state-dependent":[19],"perturbations,":[20,108],"and":[21,54,64,80,88,101,118,143,149,159,168],"input":[22],"saturation":[23],"constraints.":[24],"A":[25],"dual":[26],"critic-actor":[27],"network":[28,58,120],"structure":[29],"is":[30,73,124,137],"developed":[31],"each":[33],"player":[34],"to":[35,83,139],"reduce":[36],"the":[37,46,77,85,91,103,109,115,127,141,146,154],"Q-function":[38],"estimation":[39,122],"variance":[40,62],"caused":[41],"by":[42],"noise,":[44],"where":[45],"weighted":[47],"fusion":[48],"of":[49,90,107,114,145],"two":[50,135],"parallel":[51],"critic":[52],"networks":[53],"a":[55,96],"projection-based":[56],"actor":[57],"are":[59],"designed":[60,74],"reduction":[63],"constraint":[65,169],"satisfaction,":[66],"respectively.":[67],"An":[68,130],"learning":[70,92],"rate":[71],"strategy":[72],"based":[75],"on":[76],"temporal-difference":[78],"error":[79],"gradient":[81],"norm":[82],"balance":[84],"convergence":[86,164],"speed":[87],"stability":[89],"system.":[93],"By":[94],"constructing":[95],"composite":[97],"Lyapunov":[99],"function":[100],"combining":[102],"linear":[104],"growth":[105],"condition":[106],"uniform":[110],"ultimate":[111],"boundedness":[112],"(UUB)":[113],"state":[117],"neural":[119],"weight":[121],"errors":[123],"proven":[125],"in":[126,163],"mean-square":[128],"sense.":[129],"autonomous":[131],"driving":[132],"game":[133],"players":[136],"presented":[138],"verify":[140],"effectiveness":[142],"superiority":[144],"proposed":[147],"method,":[148],"comparative":[150],"results":[151],"show":[152],"that":[153],"outperforms":[156],"fixed-learning-rate":[157],"rule-based":[160],"PID":[161],"control":[162],"speed,":[165],"tracking":[166],"accuracy":[167],"satisfaction.":[170]},"counts_by_year":[],"updated_date":"2026-06-05T06:17:00.636019","created_date":"2026-05-29T00:00:00"}