{"id":"https://openalex.org/W3026587221","doi":"https://doi.org/10.1109/lcsys.2020.2995756","title":"Sequential Markov Games With Ordered Agents: A Bellman-Like Approach","display_name":"Sequential Markov Games With Ordered Agents: A Bellman-Like Approach","publication_year":2020,"publication_date":"2020-05-19","ids":{"openalex":"https://openalex.org/W3026587221","doi":"https://doi.org/10.1109/lcsys.2020.2995756","mag":"3026587221"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2020.2995756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2020.2995756","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","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/A5010625452","display_name":"Nachuan Yang","orcid":"https://orcid.org/0000-0002-3276-1790"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nachuan Yang","raw_affiliation_strings":["Department of Mathematics, Faculty of Science, The University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Faculty of Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040956712","display_name":"Jason J. R. Liu","orcid":"https://orcid.org/0000-0003-4100-9813"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jason J. R. Liu","raw_affiliation_strings":["Department of Mechanical Engineering, Faculty of Engineering, The University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Faculty of Engineering, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.1304,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52733286,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"4","issue":"4","first_page":"898","last_page":"903"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9980000257492065,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7667064666748047},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7451298832893372},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6802406311035156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6665118336677551},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6337572336196899},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6316579580307007},{"id":"https://openalex.org/keywords/markov-perfect-equilibrium","display_name":"Markov perfect equilibrium","score":0.6043345928192139},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5698582530021667},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.5123820900917053},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4889356195926666},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4823745787143707},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.43242523074150085},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.41947031021118164},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.40970736742019653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27427923679351807},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2454359531402588},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22235003113746643},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.22160884737968445}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7667064666748047},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7451298832893372},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6802406311035156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6665118336677551},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6337572336196899},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6316579580307007},{"id":"https://openalex.org/C67091656","wikidata":"https://www.wikidata.org/wiki/Q6771328","display_name":"Markov perfect equilibrium","level":3,"score":0.6043345928192139},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5698582530021667},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.5123820900917053},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4889356195926666},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4823745787143707},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.43242523074150085},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.41947031021118164},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.40970736742019653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27427923679351807},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2454359531402588},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22235003113746643},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.22160884737968445},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2020.2995756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2020.2995756","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W586722081","https://openalex.org/W1481965470","https://openalex.org/W1490782493","https://openalex.org/W1542941925","https://openalex.org/W1608527539","https://openalex.org/W2066538609","https://openalex.org/W2067050450","https://openalex.org/W2119567691","https://openalex.org/W2154674083","https://openalex.org/W2156268532","https://openalex.org/W2172232139","https://openalex.org/W2324627801","https://openalex.org/W2402328699","https://openalex.org/W2575731723","https://openalex.org/W2581108373","https://openalex.org/W2761465998","https://openalex.org/W2963170582","https://openalex.org/W2964191473","https://openalex.org/W2965238603","https://openalex.org/W2973189050","https://openalex.org/W2981452619","https://openalex.org/W2981546656","https://openalex.org/W2994530756","https://openalex.org/W3125686698","https://openalex.org/W4254547512","https://openalex.org/W4297823484","https://openalex.org/W4297907855","https://openalex.org/W4298023569","https://openalex.org/W6713122449"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W2808418668","https://openalex.org/W2364406457","https://openalex.org/W3105579180","https://openalex.org/W2173087131","https://openalex.org/W2383312578","https://openalex.org/W1997350370","https://openalex.org/W1574958246"],"abstract_inverted_index":{"Markov":[0,18,56,97],"games,":[1,19,98],"as":[2,39],"a":[3,40,72],"framework":[4,95],"for":[5,120],"multi-agent":[6],"reinforcement":[7],"learning,":[8],"has":[9],"been":[10],"well":[11],"investigated":[12],"in":[13,31,66,74,87],"the":[14,32,51,94,99,106,117,121,126,129],"past":[15],"decades.":[16],"In":[17],"all":[20,60],"agents":[21,61,80],"simultaneously":[22],"select":[23,64,84],"actions":[24,65,85],"at":[25],"each":[26],"state.":[27],"However":[28],"many":[29],"situations":[30],"real":[33],"world":[34],"have":[35],"to":[36,49,104,115],"be":[37],"modeled":[38],"sequential":[41,123],"process":[42,108],"with":[43,81],"ordered":[44],"agents,":[45],"which":[46],"motivates":[47],"us":[48],"widen":[50],"view":[52],"and":[53,109],"concepts":[54],"of":[55,96,128],"games":[57],"so":[58],"that":[59],"can":[62],"sequentially":[63,86],"some":[67],"order.":[68],"This":[69],"letter":[70],"studies":[71],"step":[73],"this":[75],"direction":[76],"where":[77],"exactly":[78],"two":[79],"general":[82],"objectives":[83],"an":[88],"infinite":[89],"horizon":[90],"process.":[91],"Based":[92],"on":[93],"Bellman-like":[100],"operators":[101],"are":[102,113],"proposed":[103,122],"analyze":[105],"evolutionary":[107],"dynamic":[110],"programming":[111],"algorithms":[112],"developed":[114],"derive":[116],"optimal":[118],"equilibrium":[119],"model.":[124],"Finally,":[125],"effectiveness":[127],"theoretical":[130],"results":[131],"is":[132],"illustrated":[133],"via":[134],"numerical":[135],"simulations.":[136]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}