{"id":"https://openalex.org/W1595080983","doi":"https://doi.org/10.1109/acc.2015.7171887","title":"Finite state approximations of Markov decision processes with general state and action spaces","display_name":"Finite state approximations of Markov decision processes with general state and action spaces","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1595080983","doi":"https://doi.org/10.1109/acc.2015.7171887","mag":"1595080983"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2015.7171887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2015.7171887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 American Control Conference (ACC)","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/A5029240602","display_name":"Naci Sald\u0131","orcid":"https://orcid.org/0000-0002-2677-7366"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Naci Saldi","raw_affiliation_strings":["Department of Mathematics and Statistics, Queen's University, Kingston, ON, Canada","Department of Mathematics and Statistics, Queen's University, Kingston ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen's University, Kingston ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090728745","display_name":"Tam\u00e1s Linder","orcid":"https://orcid.org/0000-0001-9993-816X"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tamas Linder","raw_affiliation_strings":["Department of Mathematics and Statistics, Queen's University, Kingston, ON, Canada","Department of Mathematics and Statistics, Queen's University, Kingston ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen's University, Kingston ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005401257","display_name":"Serdar Y\u00fcksel","orcid":"https://orcid.org/0000-0001-6099-5001"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Serdar Yuksel","raw_affiliation_strings":["Department of Mathematics and Statistics, Queen's University, Kingston, ON, Canada","Department of Mathematics and Statistics, Queen's University, Kingston ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen's University, Kingston ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029240602"],"corresponding_institution_ids":["https://openalex.org/I204722609"],"apc_list":null,"apc_paid":null,"fwci":1.7258,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87768005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9951000213623047,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"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":0.846901535987854},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6326523423194885},{"id":"https://openalex.org/keywords/finite-state","display_name":"Finite state","score":0.6130558252334595},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6124864220619202},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.611175537109375},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5851921439170837},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5801202058792114},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5446481108665466},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.5262143611907959},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5109459757804871},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5092602968215942},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.49230706691741943},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4647495150566101},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.45570454001426697},{"id":"https://openalex.org/keywords/markov-kernel","display_name":"Markov kernel","score":0.43294984102249146},{"id":"https://openalex.org/keywords/approximations-of-\u03c0","display_name":"Approximations of \u03c0","score":0.4148368239402771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3719884157180786},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.22062960267066956},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1485130488872528}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.846901535987854},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6326523423194885},{"id":"https://openalex.org/C2983497884","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite state","level":3,"score":0.6130558252334595},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6124864220619202},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.611175537109375},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5851921439170837},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5801202058792114},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5446481108665466},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5262143611907959},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5109459757804871},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5092602968215942},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.49230706691741943},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4647495150566101},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.45570454001426697},{"id":"https://openalex.org/C106666656","wikidata":"https://www.wikidata.org/wiki/Q6771323","display_name":"Markov kernel","level":5,"score":0.43294984102249146},{"id":"https://openalex.org/C193386753","wikidata":"https://www.wikidata.org/wiki/Q1130396","display_name":"Approximations of \u03c0","level":2,"score":0.4148368239402771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3719884157180786},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.22062960267066956},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1485130488872528},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acc.2015.7171887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2015.7171887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W261814290","https://openalex.org/W585548487","https://openalex.org/W891486198","https://openalex.org/W1509780496","https://openalex.org/W1562879531","https://openalex.org/W1966208686","https://openalex.org/W2010654234","https://openalex.org/W2017419329","https://openalex.org/W2046637502","https://openalex.org/W2064119715","https://openalex.org/W2068782949","https://openalex.org/W2094157328","https://openalex.org/W2134932665","https://openalex.org/W2147750403","https://openalex.org/W2168877982","https://openalex.org/W2736207102","https://openalex.org/W4210379104","https://openalex.org/W4233696721","https://openalex.org/W4244096180","https://openalex.org/W4245744559","https://openalex.org/W6624048985","https://openalex.org/W6684857301"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W3169161914","https://openalex.org/W4321379664"],"abstract_inverted_index":{"General":[0],"state":[1,37,55,64],"space":[2,40],"valued":[3],"optimal":[4,29,75],"stochastic":[5],"control":[6],"problems":[7],"are":[8,70],"often":[9],"computationally":[10],"intractable.":[11],"On":[12],"the":[13,67,74,92],"other":[14],"hand,":[15],"for":[16,27],"finite":[17,36,63,93],"state-action":[18],"models,":[19],"there":[20],"exist":[21],"powerful":[22],"computational":[23],"and":[24,38,50,53,56,104],"simulation":[25],"tools":[26],"computing":[28],"strategies.":[30],"With":[31],"this":[32],"motivation,":[33],"we":[34],"consider":[35],"action":[39,57,94],"approximations":[41,65],"of":[42,66,96],"discrete":[43,97],"time":[44,98],"Markov":[45,99],"decision":[46,100],"processes":[47],"with":[48,78,102],"discounted":[49,103],"average":[51,105],"costs":[52],"compact":[54],"spaces.":[58],"Stationary":[59],"policies":[60],"obtained":[61],"from":[62],"original":[68],"model":[69],"shown":[71],"to":[72],"approximate":[73],"stationary":[76],"policy":[77],"arbitrary":[79],"precision":[80],"under":[81],"mild":[82],"technical":[83],"conditions.":[84],"These":[85],"results":[86],"complement":[87],"recent":[88],"work":[89],"that":[90],"studied":[91],"approximation":[95],"process":[101],"costs.":[106]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}