{"id":"https://openalex.org/W4412623571","doi":"https://doi.org/10.1109/tnnls.2025.3586603","title":"Game-Theoretic Constrained Policy Optimization for Safe Reinforcement Learning","display_name":"Game-Theoretic Constrained Policy Optimization for Safe Reinforcement Learning","publication_year":2025,"publication_date":"2025-07-24","ids":{"openalex":"https://openalex.org/W4412623571","doi":"https://doi.org/10.1109/tnnls.2025.3586603","pmid":"https://pubmed.ncbi.nlm.nih.gov/40705579"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3586603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3586603","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101786094","display_name":"Changxin Zhang","orcid":"https://orcid.org/0000-0001-8829-1049"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changxin Zhang","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-8829-1049","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101668802","display_name":"Xinglong Zhang","orcid":"https://orcid.org/0000-0002-0587-2487"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinglong Zhang","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-0587-2487","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030762555","display_name":"Yixing Lan","orcid":"https://orcid.org/0000-0003-4503-643X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixing Lan","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-4503-643X","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081286464","display_name":"Hao Gao","orcid":"https://orcid.org/0000-0001-6974-4997"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Gao","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-6974-4997","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3238-745X","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":4.188,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94035983,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"36","issue":"10","first_page":"17990","last_page":"18004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6310999989509583,"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":0.6310999989509583,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.5598999857902527,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7961423993110657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5172048807144165},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.5130125880241394},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5109466910362244},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3982802629470825},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3726831078529358},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35086676478385925},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.24732697010040283},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23643893003463745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19306161999702454},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.14221155643463135}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7961423993110657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5172048807144165},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.5130125880241394},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5109466910362244},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3982802629470825},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3726831078529358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35086676478385925},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.24732697010040283},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23643893003463745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19306161999702454},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.14221155643463135}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3586603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3586603","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40705579","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40705579","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G62426012","display_name":null,"funder_award_id":"U24A20279","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G704626557","display_name":null,"funder_award_id":"2024RC3145","funder_id":"https://openalex.org/F4320330206","funder_display_name":"Science and Technology Program of Hunan Province"},{"id":"https://openalex.org/G7763311295","display_name":null,"funder_award_id":"62306325","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8354495100","display_name":null,"funder_award_id":"U21A20518","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/F4320330206","display_name":"Science and Technology Program of Hunan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W168473977","https://openalex.org/W1907356258","https://openalex.org/W1977655452","https://openalex.org/W2006439090","https://openalex.org/W2089415692","https://openalex.org/W2121180068","https://openalex.org/W2158782408","https://openalex.org/W2209913494","https://openalex.org/W2963525569","https://openalex.org/W2963575966","https://openalex.org/W2968547875","https://openalex.org/W2998619042","https://openalex.org/W3006344226","https://openalex.org/W3033003934","https://openalex.org/W3093201391","https://openalex.org/W3103475966","https://openalex.org/W3127561923","https://openalex.org/W4206497039","https://openalex.org/W4224216677","https://openalex.org/W4254547512","https://openalex.org/W4285600796","https://openalex.org/W4293370597","https://openalex.org/W4379527413","https://openalex.org/W4382318502","https://openalex.org/W4389775604","https://openalex.org/W4390576807","https://openalex.org/W4392114294","https://openalex.org/W4401608518","https://openalex.org/W4406610232"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Safe":[0],"reinforcement":[1],"learning":[2,113,134,162,168],"(RL)":[3],"aims":[4],"to":[5,17,90,99,146,163,221],"optimize":[6],"the":[7,23,35,74,92,112,127,131,137,143,147,181,231],"task":[8,87,210,225],"performance":[9],"with":[10,53,82,115,120,142],"safety":[11],"guarantees.":[12],"One":[13],"common":[14],"modeling":[15],"scheme":[16],"study":[18],"safe":[19,31,61,202],"RL":[20,32,62,203],"problems":[21],"is":[22,157],"constrained":[24,66],"Markov":[25,80],"decision":[26],"process":[27],"(CMDP).":[28],"However,":[29],"current":[30],"methods":[33],"within":[34],"CMDP":[36,75],"framework":[37],"face":[38],"challenges":[39],"in":[40,205],"tradeoffs":[41],"among":[42],"various":[43,212],"objectives":[44,102],"and":[45,170,187,211,227],"gradient":[46,189],"conflicts":[47,190],"of":[48,130,136,173,183,224],"policy":[49,67,161,193],"updating.":[50,194],"To":[51],"cope":[52],"these":[54],"challenges,":[55],"this":[56],"article":[57],"presents":[58],"a":[59,78,86,121,151,206],"novel":[60,152],"approach":[63,72],"called":[64],"game-theoretic":[65],"optimization":[68],"(GCPO).":[69],"The":[70,133,167],"proposed":[71],"formulates":[73],"problem":[76],"as":[77],"general-sum":[79],"game":[81],"multiple":[83,116],"players,":[84],"where":[85],"player":[88],"seeks":[89],"maximize":[91],"reward":[93],"objective,":[94,123],"while":[95],"constraint":[96,101,165,171,228],"players":[97],"aim":[98],"minimize":[100],"until":[103],"they":[104],"are":[105,175],"fulfilled.":[106],"By":[107],"doing":[108],"so,":[109],"GCPO":[110,138,174,179,199,218],"adopts":[111],"mode":[114],"subpolicies,":[117],"each":[118],"aligned":[119],"distinct":[122],"that":[124,198],"collectively":[125],"constitute":[126],"overall":[128],"behavior":[129],"agent.":[132],"convergence":[135,169],"can":[139],"be":[140],"ensured":[141],"contraction":[144],"mapping":[145],"Nash":[148],"equilibrium.":[149],"Furthermore,":[150],"dominant":[153],"timescale":[154],"update":[155],"rule":[156],"presented":[158],"for":[159,233],"multiplayer":[160],"guarantee":[164],"satisfaction.":[166],"satisfaction":[172],"theoretically":[176],"analyzed.":[177],"Consequently,":[178],"eliminates":[180],"necessity":[182],"tuning":[184],"tradeoff":[185],"parameters":[186],"mitigates":[188],"during":[191],"multiobjective":[192],"Experimental":[195],"results":[196],"show":[197],"outperforms":[200],"state-of-the-art":[201],"algorithms":[204],"quadrotor":[207],"trajectory":[208],"tracking":[209],"high-dimensional":[213],"robot":[214],"locomotion":[215],"benchmarks.":[216],"Moreover,":[217],"exhibits":[219],"robustness":[220],"diverse":[222],"scales":[223],"rewards":[226],"costs":[229],"without":[230],"need":[232],"intricate":[234],"tradeoffs.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}