{"id":"https://openalex.org/W2029229938","doi":"https://doi.org/10.1080/00207720701596656","title":"Error bounds of optimization algorithms for semi-Markov decision processes","display_name":"Error bounds of optimization algorithms for semi-Markov decision processes","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W2029229938","doi":"https://doi.org/10.1080/00207720701596656","mag":"2029229938"},"language":"en","primary_location":{"id":"doi:10.1080/00207720701596656","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207720701596656","pdf_url":null,"source":{"id":"https://openalex.org/S129640837","display_name":"International Journal of Systems Science","issn_l":"0020-7721","issn":["0020-7721","1464-5319"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Systems Science","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":null,"display_name":"Tang Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tang Hao","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology","School of Computer and Information, Hefei University of Technology, Hefei, Anhui, P.R.China#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]},{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology, Hefei, Anhui, P.R.China#TAB#","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702382","display_name":"Baoqun Yin","orcid":"https://orcid.org/0000-0002-5225-4729"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Baoqun","raw_affiliation_strings":["University of Science and Technology of China","Department of Automation, University of Science and Technology of China , Hefei, Anhui, P.R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China , Hefei, Anhui, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069802328","display_name":"Hongsheng Xi","orcid":"https://orcid.org/0000-0002-5747-9732"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Hongsheng","raw_affiliation_strings":["University of Science and Technology of China","Department of Automation, University of Science and Technology of China , Hefei, Anhui, P.R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China , Hefei, Anhui, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":1.4509,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85433604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"38","issue":"9","first_page":"725","last_page":"736"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9957000017166138,"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":0.9957000017166138,"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/T10142","display_name":"Formal Methods in Verification","score":0.987500011920929,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9593999981880188,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/markov-decision-process","display_name":"Markov decision process","score":0.7479711771011353},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6608654260635376},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6304923295974731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.486057311296463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.480716735124588},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4566257894039154},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4350408613681793},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4256080389022827},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.41746583580970764},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.41185706853866577},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3566175401210785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13363566994667053},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11148375272750854},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08959287405014038}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7479711771011353},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6608654260635376},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6304923295974731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.486057311296463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.480716735124588},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4566257894039154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4350408613681793},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4256080389022827},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41746583580970764},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.41185706853866577},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3566175401210785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13363566994667053},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11148375272750854},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08959287405014038}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/00207720701596656","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207720701596656","pdf_url":null,"source":{"id":"https://openalex.org/S129640837","display_name":"International Journal of Systems Science","issn_l":"0020-7721","issn":["0020-7721","1464-5319"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Systems Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7699999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322990","display_name":"Sichuan University","ror":"https://ror.org/011ashp19"},{"id":"https://openalex.org/F4320325599","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W157071335","https://openalex.org/W184225095","https://openalex.org/W967014446","https://openalex.org/W1504402415","https://openalex.org/W1515851193","https://openalex.org/W1576452626","https://openalex.org/W1608333589","https://openalex.org/W2002415962","https://openalex.org/W2021231433","https://openalex.org/W2035530892","https://openalex.org/W2048309236","https://openalex.org/W2070340123","https://openalex.org/W2089742512","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2123334156","https://openalex.org/W2154454517","https://openalex.org/W2171033527","https://openalex.org/W2334782222","https://openalex.org/W2367966666","https://openalex.org/W3026026050","https://openalex.org/W4214717370","https://openalex.org/W4248850015","https://openalex.org/W4253991977","https://openalex.org/W4307347247"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W3096874164","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W1985560493","https://openalex.org/W2294884454","https://openalex.org/W2937181779"],"abstract_inverted_index":{"Cao's":[0],"work":[1],"shows":[2],"that,":[3],"by":[4],"defining":[5],"an":[6,28,65,183],"\u03b1-dependent":[7],"equivalent":[8],"infinitesimal":[9],"generator":[10],"A":[11,57,74],"\u03b1,":[12],"a":[13,71,77,104,123,128,191],"semi-Markov":[14],"decision":[15,31],"process":[16,32],"(SMDP)":[17],"with":[18],"both":[19],"average-":[20],"and":[21,34,56,76,80,106,127,152,155,168,196],"discounted-cost":[22],"criteria":[23],"can":[24,39,141,156],"be":[25,41,142,157],"treated":[26],"as":[27,91,165],"\u03b1-equivalent":[29],"Markov":[30,67,153],"(MDP),":[33],"the":[35,101,107,119,146,187,198],"performance":[36,89],"potential":[37,55],"theory":[38],"also":[40],"developed":[42],"for":[43,54,70,122],"SMDPs.":[44],"In":[45],"this":[46],"work,":[47],"we":[48,63,85,117,181],"focus":[49],"on":[50,110,186],"establishing":[51],"error":[52,120,200],"bounds":[53,121],"\u03b1-based":[58],"iterative":[59],"optimization":[60,162],"methods.":[61],"First,":[62],"introduce":[64],"\u03b1-uniformized":[66],"chain":[68],"(UMC)":[69],"SMDP":[72,105],"via":[73],"\u03b1":[75],"uniformized":[78],"parameter,":[79],"show":[81,197],"their":[82,88],"relations.":[83],"Especially,":[84],"obtain":[86],"that":[87,100],"potentials,":[90],"solutions":[92],"of":[93,103,190],"corresponding":[94,199],"Poisson":[95],"equations,":[96],"are":[97,112,177],"proportional,":[98],"so":[99],"studies":[102],"\u03b1-UMC":[108],"based":[109],"potentials":[111],"unified.":[113],"Using":[114],"these":[115],"relations,":[116],"derive":[118],"potential-based":[124],"policy-iteration":[125],"algorithm":[126],"value-iteration":[129],"algorithm,":[130],"respectively,":[131],"when":[132],"there":[133],"exist":[134],"various":[135],"calculation":[136],"errors.":[137],"The":[138],"obtained":[139],"results":[140],"applied":[143],"directly":[144],"to":[145,159],"special":[147],"models,":[148],"i.e.,":[149],"continuous-time":[150],"MDPs":[151],"chains,":[154],"extended":[158],"some":[160],"simulation-based":[161],"methods":[163],"such":[164],"reinforcement":[166],"learning":[167],"neuro-dynamic":[169],"programming,":[170],"where":[171],"estimation":[172],"errors":[173,176],"or":[174],"approximation":[175],"common":[178],"cases.":[179],"Finally,":[180],"give":[182],"application":[184],"example":[185],"look-ahead":[188],"control":[189],"conveyor-serviced":[192],"production":[193],"station":[194],"(CSPS),":[195],"bounds.":[201]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}