{"id":"https://openalex.org/W2104198943","doi":"https://doi.org/10.1109/cdc.2005.1583466","title":"On Solving Controlled Markov Set-Chains via Multi-Policy Improvement","display_name":"On Solving Controlled Markov Set-Chains via Multi-Policy Improvement","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2104198943","doi":"https://doi.org/10.1109/cdc.2005.1583466","mag":"2104198943"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2005.1583466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2005.1583466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th IEEE Conference on Decision and Control","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041693183","display_name":"Hyeong Soo Chang","orcid":"https://orcid.org/0000-0003-3298-0018"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeong Soo Chang","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, Seoul, Korea. hschang@sogang.ac.kr","Department of Computer Science and Engineering, Sogang University, Seoul, Korea hschang@sogang.ac.kr"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, Korea. hschang@sogang.ac.kr","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, Korea hschang@sogang.ac.kr","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070385137","display_name":"Edwin K. P. Chong","orcid":"https://orcid.org/0000-0002-7622-4815"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E.K.P. Chong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO, USA","COLORADO STATE UNIVERSITY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I92446798"]},{"raw_affiliation_string":"COLORADO STATE UNIVERSITY","institution_ids":["https://openalex.org/I92446798"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8058","last_page":"8063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9830999970436096,"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/T10142","display_name":"Formal Methods in Verification","score":0.9830999970436096,"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/T11125","display_name":"Petri Nets in System Modeling","score":0.9793000221252441,"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":0.9763000011444092,"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":0.8640041351318359},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.795127272605896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6957427263259888},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6487928032875061},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5743779540061951},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5496212244033813},{"id":"https://openalex.org/keywords/markov-kernel","display_name":"Markov kernel","score":0.4490441381931305},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4402255415916443},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.415056049823761},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.40141141414642334},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.205664724111557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19411984086036682}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8640041351318359},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.795127272605896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6957427263259888},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6487928032875061},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5743779540061951},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5496212244033813},{"id":"https://openalex.org/C106666656","wikidata":"https://www.wikidata.org/wiki/Q6771323","display_name":"Markov kernel","level":5,"score":0.4490441381931305},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4402255415916443},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.415056049823761},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.40141141414642334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.205664724111557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19411984086036682},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2005.1583466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2005.1583466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th IEEE Conference on Decision and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W427836156","https://openalex.org/W1988217924","https://openalex.org/W2034713309","https://openalex.org/W2036931518","https://openalex.org/W2058811924","https://openalex.org/W2069045459","https://openalex.org/W2083600812","https://openalex.org/W2119567691","https://openalex.org/W2334782222","https://openalex.org/W4213347800"],"related_works":["https://openalex.org/W2130519334","https://openalex.org/W1985664346","https://openalex.org/W2382132287","https://openalex.org/W1493775604","https://openalex.org/W2363310627","https://openalex.org/W2353444478","https://openalex.org/W4240129243","https://openalex.org/W1504767525","https://openalex.org/W4360597163","https://openalex.org/W3216708645"],"abstract_inverted_index":{"We":[0,54],"present":[1],"formal":[2],"methods":[3,21,37],"of":[4,25,43],"improving":[5],"multiple":[6],"policies":[7],"for":[8,28,40,47],"solving":[9,29,49],"controlled":[10],"Markov":[11,30,44],"set-chains":[12,45],"with":[13],"infinite-horizon":[14],"iscounted":[15],"reward":[16],"criteria.":[17],"The":[18],"multi-policy":[19],"improvement":[20,68],"follow":[22],"the":[23],"spirit":[24],"parallel":[26],"rollout":[27],"decision":[31],"processes":[32],"(MDPs).":[33],"In":[34],"particular,":[35],"these":[36],"are":[38],"useful":[39],"on-line":[41],"control":[42],"and":[46],"approximately":[48],"MDPs":[50],"via":[51],"state":[52],"aggregation.":[53],"further":[55],"discuss":[56],"issues":[57],"on":[58,65],"designing":[59],"a":[60],"policy-iteration":[61],"type":[62],"algorithm":[63],"based":[64],"our":[66],"policy":[67],"methods.":[69]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}