{"id":"https://openalex.org/W2079836336","doi":"https://doi.org/10.1109/acc.2012.6315187","title":"A two-phase time aggregation algorithm for average cost Markov decision processes","display_name":"A two-phase time aggregation algorithm for average cost Markov decision processes","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2079836336","doi":"https://doi.org/10.1109/acc.2012.6315187","mag":"2079836336"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2012.6315187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2012.6315187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5016483768","display_name":"Edilson F. Arruda","orcid":"https://orcid.org/0000-0002-9835-352X"},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"E. F. Arruda","raw_affiliation_strings":["PEP/COPPE/UFRJ, Federal University of Rio de Janeiro, Rio de Janeiro, Rio de Janeiro, Brazil","Federal University of Rio de Janeiro - UFRJ, PEP/COPPE/UFRJ, Caixa Postal 68507, Cep 21941-972, Rio de Janeiro RJ, Brazil"],"affiliations":[{"raw_affiliation_string":"PEP/COPPE/UFRJ, Federal University of Rio de Janeiro, Rio de Janeiro, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]},{"raw_affiliation_string":"Federal University of Rio de Janeiro - UFRJ, PEP/COPPE/UFRJ, Caixa Postal 68507, Cep 21941-972, Rio de Janeiro RJ, Brazil","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081242243","display_name":"Marcelo D. Fragoso","orcid":"https://orcid.org/0000-0001-6299-6614"},"institutions":[{"id":"https://openalex.org/I4210142352","display_name":"Laborat\u00f3rio Nacional de Computa\u00e7\u00e3o Cient\u00edfica","ror":"https://ror.org/0498ekt05","country_code":"BR","type":"government","lineage":["https://openalex.org/I4210142352"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"M. D. Fragoso","raw_affiliation_strings":["National Laboratory for Scientific Computing, Petropolis, Rio de Janeiro, Brazil","National Laboratory for Scientific Computing - LNCC/CNPq, Av. Get\u00falio Vargas 333, Petr\u00f3polis, RJ, CEP 25651-070, Brazil"],"affiliations":[{"raw_affiliation_string":"National Laboratory for Scientific Computing, Petropolis, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I4210142352"]},{"raw_affiliation_string":"National Laboratory for Scientific Computing - LNCC/CNPq, Av. Get\u00falio Vargas 333, Petr\u00f3polis, RJ, CEP 25651-070, Brazil","institution_ids":["https://openalex.org/I4210142352"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016483768"],"corresponding_institution_ids":["https://openalex.org/I122140584"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11523963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1 2","issue":null,"first_page":"1615","last_page":"1620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9940999746322632,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9822999835014343,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7695463299751282},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6616803407669067},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.654163658618927},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6457277536392212},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6320546269416809},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5728296637535095},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5698750615119934},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5318654775619507},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4967671036720276},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4958091676235199},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.47513702511787415},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26666173338890076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1774095892906189},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16777250170707703},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13417282700538635}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7695463299751282},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6616803407669067},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.654163658618927},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6457277536392212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6320546269416809},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5728296637535095},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5698750615119934},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5318654775619507},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4967671036720276},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4958091676235199},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.47513702511787415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26666173338890076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1774095892906189},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16777250170707703},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13417282700538635},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/acc.2012.6315187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2012.6315187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.soton.ac.uk:445897","is_oa":false,"landing_page_url":"https://eprints.soton.ac.uk/445897/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1547105496","https://openalex.org/W1550698229","https://openalex.org/W1576452626","https://openalex.org/W1601081659","https://openalex.org/W1968115484","https://openalex.org/W1979894788","https://openalex.org/W1993033704","https://openalex.org/W1995107792","https://openalex.org/W2018694622","https://openalex.org/W2041621488","https://openalex.org/W2062820925","https://openalex.org/W2079806887","https://openalex.org/W2079830915","https://openalex.org/W2098432798","https://openalex.org/W2100857832","https://openalex.org/W2103263764","https://openalex.org/W2103406407","https://openalex.org/W2106471678","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2123952007","https://openalex.org/W2124821240","https://openalex.org/W2139418546","https://openalex.org/W2160126685","https://openalex.org/W2334782222","https://openalex.org/W2487144912","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4245296547"],"related_works":["https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W4388236136","https://openalex.org/W2807018115","https://openalex.org/W2413828414","https://openalex.org/W4200250224","https://openalex.org/W2367222340","https://openalex.org/W2126560268","https://openalex.org/W1841898224"],"abstract_inverted_index":{"<p>This":[0],"paper":[1],"introduces":[2],"a":[3,35,43,67,84],"two-phase":[4],"approach":[5],"to":[6,48,52],"solve":[7],"average":[8],"cost":[9],"Markov":[10],"decision":[11],"processes,":[12],"which":[13],"is":[14,29,46,59,81,88],"based":[15],"on":[16],"state":[17,40,55],"space":[18],"embedding":[19],"or":[20,83],"time":[21,27,87],"aggregation.":[22],"In":[23],"the":[24,39,50,53,63,72],"first":[25],"phase,":[26],"aggregation":[28],"applied":[30,47,78],"for":[31],"policy":[32,68],"evaluation":[33,51,58],"in":[34,62,66],"prescribed":[36,85],"subset":[37],"of":[38],"space,":[41],"and":[42,71],"novel":[44],"result":[45],"expand":[49],"whole":[54],"space.":[56],"This":[57],"then":[60,76],"used":[61],"second":[64],"phase":[65],"improvement":[69],"step,":[70],"two":[73],"phases":[74],"are":[75],"sequentially":[77],"until":[79],"convergence":[80],"attained":[82],"running":[86],"exceeded.</p>":[89]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}