{"id":"https://openalex.org/W3181585847","doi":"https://doi.org/10.1109/icps49255.2021.9468152","title":"A Class of Optimal Control Problem for Stochastic Discrete-Time Systems with Average Reward Reinforcement Learning","display_name":"A Class of Optimal Control Problem for Stochastic Discrete-Time Systems with Average Reward Reinforcement Learning","publication_year":2021,"publication_date":"2021-05-10","ids":{"openalex":"https://openalex.org/W3181585847","doi":"https://doi.org/10.1109/icps49255.2021.9468152","mag":"3181585847"},"language":"en","primary_location":{"id":"doi:10.1109/icps49255.2021.9468152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icps49255.2021.9468152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 4th IEEE International Conference on Industrial Cyber-Physical Systems (ICPS)","raw_type":"proceedings-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/A5077045940","display_name":"Yifan Hu","orcid":"https://orcid.org/0000-0003-0756-6157"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifan Hu","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030933117","display_name":"Junjie Fu","orcid":"https://orcid.org/0000-0002-1528-8727"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Fu","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021516964","display_name":"Yuezu Lv","orcid":"https://orcid.org/0000-0002-7757-9028"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuezu Lv","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077045940"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12708504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"94","issue":null,"first_page":"829","last_page":"834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9925000071525574,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9401000142097473,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8675742149353027},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8446908593177795},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.6686004996299744},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6195989847183228},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5987487435340881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5818723440170288},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5741086602210999},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5529661774635315},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.534285306930542},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4852173626422882},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4849091172218323},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.42902541160583496},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4149530231952667},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34285080432891846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2780124843120575},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07152518630027771}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8675742149353027},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8446908593177795},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.6686004996299744},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6195989847183228},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5987487435340881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5818723440170288},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5741086602210999},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5529661774635315},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.534285306930542},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4852173626422882},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4849091172218323},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.42902541160583496},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4149530231952667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34285080432891846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2780124843120575},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07152518630027771},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icps49255.2021.9468152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icps49255.2021.9468152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 4th IEEE International Conference on Industrial Cyber-Physical Systems (ICPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1549353711","https://openalex.org/W1595516097","https://openalex.org/W1983523797","https://openalex.org/W2002007892","https://openalex.org/W2024303516","https://openalex.org/W2028145673","https://openalex.org/W2044605743","https://openalex.org/W2050838777","https://openalex.org/W2071983464","https://openalex.org/W2081374871","https://openalex.org/W2081514674","https://openalex.org/W2101242010","https://openalex.org/W2101915445","https://openalex.org/W2104017958","https://openalex.org/W2105402422","https://openalex.org/W2119567691","https://openalex.org/W2132858840","https://openalex.org/W2154204727","https://openalex.org/W2331243380","https://openalex.org/W2333120204","https://openalex.org/W2914054366","https://openalex.org/W4214717370","https://openalex.org/W6675043515"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2101748387","https://openalex.org/W2357975469","https://openalex.org/W4380550992","https://openalex.org/W4322760752","https://openalex.org/W3096874164","https://openalex.org/W2146763310","https://openalex.org/W3167472281","https://openalex.org/W2937181779","https://openalex.org/W2367195854"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,33],"class":[4],"of":[5,25,97],"optimal":[6,22,53],"control":[7,23],"problem":[8,24,36],"for":[9,37],"stochastic":[10,27],"discrete-time":[11,28],"systems":[12],"is":[13,30,43,55,86],"addressed":[14],"by":[15],"average":[16,59],"reward":[17,60],"reinforcement":[18,83],"learning.":[19],"First,":[20],"the":[21,26,46,52,58,71,77,95,98],"system":[29,72],"transformed":[31],"into":[32],"sequential":[34],"decision":[35,39],"Markov":[38],"process":[40],"(MDP).":[41],"It":[42],"proven":[44],"that":[45],"admissible":[47],"policies":[48],"are":[49,73,91],"gain-optimal":[50],"and":[51],"policy":[54],"bias-optimal":[56],"with":[57],"criterion,":[61],"respectively.":[62],"Then,":[63],"sufficient":[64],"conditions":[65],"to":[66,93],"almost":[67],"surely":[68],"(a.s.)":[69],"stabilize":[70],"proposed.":[74],"Based":[75],"on":[76],"above":[78],"results,":[79],"an":[80],"on-policy":[81],"average-reward-based":[82],"learning":[84],"algorithm":[85],"developed.":[87],"Finally,":[88],"simulation":[89],"results":[90],"provided":[92],"illustrate":[94],"effectiveness":[96],"proposed":[99],"algorithm.":[100]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}