{"id":"https://openalex.org/W4404914401","doi":"https://doi.org/10.1109/tac.2024.3510596","title":"Approximate Policy Iteration for Robust Stochastic Control of Multiagent Markov Decision Processes","display_name":"Approximate Policy Iteration for Robust Stochastic Control of Multiagent Markov Decision Processes","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4404914401","doi":"https://doi.org/10.1109/tac.2024.3510596"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2024.3510596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3510596","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.rug.nl/en/publications/9fdb4887-ef67-4b4b-93b2-215a27ec470d","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053614102","display_name":"Feng Huang","orcid":"https://orcid.org/0000-0002-6725-8263"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng Huang","raw_affiliation_strings":["Center for Systems and Control, College of Engineering, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Systems and Control, College of Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021403340","display_name":"Ming Cao","orcid":"https://orcid.org/0000-0001-5472-562X"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ming Cao","raw_affiliation_strings":["ENTEG, Faculty of Science and Engineering, University of Groningen, Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"ENTEG, Faculty of Science and Engineering, University of Groningen, Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100447536","display_name":"Long Wang","orcid":"https://orcid.org/0000-0001-5600-8157"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Wang","raw_affiliation_strings":["Center for Systems and Control, College of Engineering, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Systems and Control, College of Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053614102"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.6762,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76836244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"70","issue":"6","first_page":"3587","last_page":"3602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8478999733924866,"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":0.8478999733924866,"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/T11182","display_name":"Auction Theory and Applications","score":0.8271999955177307,"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"}},{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.8205000162124634,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8246604204177856},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5670070648193359},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5537720918655396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5524446964263916},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.49686625599861145},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.47654658555984497},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.41511720418930054},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3826923668384552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3582068085670471},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.2680216133594513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20364409685134888},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13951274752616882},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11297929286956787},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0890573263168335}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8246604204177856},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5670070648193359},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5537720918655396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5524446964263916},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.49686625599861145},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47654658555984497},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.41511720418930054},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3826923668384552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3582068085670471},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2680216133594513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20364409685134888},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13951274752616882},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11297929286956787},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0890573263168335},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tac.2024.3510596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3510596","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"},{"id":"pmh:oai:pure.rug.nl:openaire/9fdb4887-ef67-4b4b-93b2-215a27ec470d","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/9fdb4887-ef67-4b4b-93b2-215a27ec470d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Huang, F, Cao, M & Wang, L 2025, 'Approximate Policy Iteration for Robust Stochastic Control of Multi-agent Markov Decision Processes', IEEE Transactions on Automatic Control, vol. 70, no. 6, pp. 3587-3602. https://doi.org/10.1109/TAC.2024.3510596","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/9fdb4887-ef67-4b4b-93b2-215a27ec470d","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/9fdb4887-ef67-4b4b-93b2-215a27ec470d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Huang, F, Cao, M & Wang, L 2025, 'Approximate Policy Iteration for Robust Stochastic Control of Multi-agent Markov Decision Processes', IEEE Transactions on Automatic Control, vol. 70, no. 6, pp. 3587-3602. https://doi.org/10.1109/TAC.2024.3510596","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.rug.nl:openaire/9fdb4887-ef67-4b4b-93b2-215a27ec470d","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/9fdb4887-ef67-4b4b-93b2-215a27ec470d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Huang, F, Cao, M & Wang, L 2025, 'Approximate Policy Iteration for Robust Stochastic Control of Multi-agent Markov Decision Processes', IEEE Transactions on Automatic Control, vol. 70, no. 6, pp. 3587-3602. https://doi.org/10.1109/TAC.2024.3510596","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3181167558","display_name":null,"funder_award_id":"62036002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6403596008","display_name":null,"funder_award_id":"ERC-CoG-771687","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"},{"id":"https://openalex.org/G7611946713","display_name":null,"funder_award_id":"201906010075","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1918371733","https://openalex.org/W1965878388","https://openalex.org/W1986872757","https://openalex.org/W2006301680","https://openalex.org/W2066111511","https://openalex.org/W2069045459","https://openalex.org/W2096035449","https://openalex.org/W2096145798","https://openalex.org/W2099618002","https://openalex.org/W2107544712","https://openalex.org/W2115118348","https://openalex.org/W2138966161","https://openalex.org/W2156194062","https://openalex.org/W2168565265","https://openalex.org/W2240086230","https://openalex.org/W2501656778","https://openalex.org/W2767257775","https://openalex.org/W2963525569","https://openalex.org/W2968526727","https://openalex.org/W2978862222","https://openalex.org/W2991046523","https://openalex.org/W3035235874","https://openalex.org/W3035285337","https://openalex.org/W3036286896","https://openalex.org/W3044908040","https://openalex.org/W3046016382","https://openalex.org/W3094399342","https://openalex.org/W3119186746","https://openalex.org/W3121342653","https://openalex.org/W3130610232","https://openalex.org/W3135349069","https://openalex.org/W3174652807","https://openalex.org/W3175144487","https://openalex.org/W3197526462","https://openalex.org/W3209754935","https://openalex.org/W4254547512","https://openalex.org/W6631137000","https://openalex.org/W6639430172","https://openalex.org/W6677549092","https://openalex.org/W6681342480","https://openalex.org/W6718836005","https://openalex.org/W6735677848","https://openalex.org/W6764339904","https://openalex.org/W6785517317","https://openalex.org/W6802038118"],"related_works":["https://openalex.org/W1660242800","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2315999538","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"In":[0],"stochastic":[1,66],"dynamic":[2,146],"environments,":[3],"multiagent":[4,22,70],"Markov":[5,71],"decision":[6,72],"processes":[7,73],"have":[8],"emerged":[9],"as":[10],"a":[11,64,78,86,97,107,122,126,151],"versatile":[12],"paradigm":[13],"for":[14,101,114,133,158],"studying":[15],"sequential":[16,185],"decision-making":[17],"problems":[18],"of":[19,27,55,69,90,99,110,116,131,177,184],"fully":[20],"cooperative":[21],"systems.":[23],"However,":[24],"the":[25,28,53,94,175,178,182],"optimality":[26,113],"derived":[29],"policies":[30,57,132],"is":[31,83],"usually":[32],"sensitive":[33],"to":[34,43,58,84,162,173,188],"model":[35,183],"parameters,":[36,61],"which":[37],"are":[38,171],"typically":[39],"unknown":[40],"and":[41,93,105,136],"required":[42,164],"be":[44],"estimated":[45],"from":[46],"noisy":[47],"data":[48],"in":[49],"practice.":[50],"To":[51,119],"investigate":[52],"sensitivity":[54],"optimal":[56],"these":[59],"uncertain":[60,189],"we":[62,124],"study":[63],"robust":[65,111,127,145],"control":[67],"problem":[68],"where":[74],"all":[75,91,117,134],"agents":[76,92,135],"constitute":[77],"centralized":[79],"controller":[80],"whose":[81],"goal":[82],"seek":[85,120],"maximal":[87],"long-term":[88],"return":[89],"uncertainty":[95],"plays":[96],"role":[98],"disturbance":[100],"achieving":[102],"this":[103],"goal,":[104],"provide":[106],"solution":[108],"concept":[109],"team":[112],"decisions":[115],"agents.":[118],"such":[121],"solution,":[123],"develop":[125],"iterative":[128],"learning":[129],"algorithm":[130,179],"present":[137],"its":[138],"convergence":[139,153],"analysis.":[140],"This":[141],"algorithm,":[142],"compared":[143],"with":[144],"programming,":[147],"not":[148],"only":[149],"possesses":[150],"faster":[152],"rate,":[154],"but":[155],"also":[156],"allows":[157],"using":[159],"approximation":[160],"calculations":[161],"alleviate":[163],"computational":[165],"resources.":[166],"Moreover,":[167],"some":[168],"numerical":[169],"simulations":[170],"presented":[172],"demonstrate":[174],"effectiveness":[176],"by":[180],"extending":[181],"social":[186],"dilemmas":[187],"scenarios.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}