{"id":"https://openalex.org/W1991138660","doi":"https://doi.org/10.1109/icnsc.2012.6204909","title":"Reinforcement learning algorithms for semi-Markov decision processes with average reward","display_name":"Reinforcement learning algorithms for semi-Markov decision processes with average reward","publication_year":2012,"publication_date":"2012-04-01","ids":{"openalex":"https://openalex.org/W1991138660","doi":"https://doi.org/10.1109/icnsc.2012.6204909","mag":"1991138660"},"language":"en","primary_location":{"id":"doi:10.1109/icnsc.2012.6204909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnsc.2012.6204909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2012 9th IEEE International Conference on Networking, Sensing and Control","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/A5100677178","display_name":"Yanjie Li","orcid":"https://orcid.org/0000-0001-7890-9677"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanjie Li","raw_affiliation_strings":["Shenzhen Graduate School, Harbin Institute of Technology, China","Harbin Institute of technology Shenzhen Graduate School"],"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of technology Shenzhen Graduate School","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100677178"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.07362722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"15","issue":null,"first_page":"157","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9811999797821045,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9575999975204468,"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":0.908812403678894},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8688088655471802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6815127730369568},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5923110842704773},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5884351134300232},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5589138865470886},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5060839056968689},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4854329228401184},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42734119296073914},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4211307466030121},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36411532759666443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35834801197052},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35638344287872314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24914827942848206},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08537331223487854}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.908812403678894},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8688088655471802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6815127730369568},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5923110842704773},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5884351134300232},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5589138865470886},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5060839056968689},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4854329228401184},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42734119296073914},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4211307466030121},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36411532759666443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35834801197052},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35638344287872314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24914827942848206},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08537331223487854},{"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/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icnsc.2012.6204909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnsc.2012.6204909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2012 9th IEEE International Conference on Networking, Sensing and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W142462678","https://openalex.org/W628582992","https://openalex.org/W1519485122","https://openalex.org/W1602007439","https://openalex.org/W1998645260","https://openalex.org/W2009303086","https://openalex.org/W2075754841","https://openalex.org/W2096899507","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2101915445","https://openalex.org/W2117941808","https://openalex.org/W2119717200","https://openalex.org/W2120465407","https://openalex.org/W2121494316","https://openalex.org/W2123334156","https://openalex.org/W2144446635","https://openalex.org/W2153947321","https://openalex.org/W2154204727","https://openalex.org/W2155027007","https://openalex.org/W2161753411","https://openalex.org/W2164056559","https://openalex.org/W2169293926","https://openalex.org/W2334782222","https://openalex.org/W2484957131","https://openalex.org/W3041202696","https://openalex.org/W3103182070","https://openalex.org/W3151298155","https://openalex.org/W4205326910","https://openalex.org/W4206698392","https://openalex.org/W4214717370","https://openalex.org/W4302805353","https://openalex.org/W6605831686","https://openalex.org/W6630939357","https://openalex.org/W6635883855","https://openalex.org/W6682802936","https://openalex.org/W6683204974","https://openalex.org/W6683826586","https://openalex.org/W6684199269"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2182304831","https://openalex.org/W2145363145","https://openalex.org/W3168977894"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"study":[4],"reinforcement":[5],"learning":[6],"(RL)":[7],"algorithms":[8,40],"based":[9],"on":[10],"a":[11,72],"perspective":[12],"of":[13,60,67,98],"performance":[14,27],"sensitivity":[15,28],"analysis":[16,29],"for":[17,30,41,84],"SMDPs":[18,31,43,92],"with":[19,32],"average":[20,33,62],"reward.":[21,34],"We":[22],"present":[23],"the":[24,49,58,65,79,99],"results":[25],"about":[26],"On":[35],"these":[36],"bases,":[37],"two":[38],"RL":[39,54],"average-reward":[42],"are":[44],"studied.":[45],"One":[46],"algorithm":[47,70,83],"is":[48,71],"relative":[50],"value":[51],"iteration":[52],"(RVI)":[53],"algorithm,":[55,76],"which":[56,77],"avoids":[57],"estimation":[59,75,82],"optimal":[61],"reward":[63],"in":[64],"process":[66],"learning.":[68],"Another":[69],"policy":[73,80],"gradient":[74,81],"extends":[78],"discrete":[85],"time":[86],"Markov":[87],"decision":[88],"processes":[89],"(MDPs)":[90],"to":[91],"and":[93],"only":[94],"requires":[95],"half":[96],"storage":[97],"existing":[100],"algorithm.":[101]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}