{"id":"https://openalex.org/W2168809087","doi":"https://doi.org/10.1109/adprl.2009.4927531","title":"Adaptive computation of optimal nonrandomized policies in constrained average-reward MDPs","display_name":"Adaptive computation of optimal nonrandomized policies in constrained average-reward MDPs","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W2168809087","doi":"https://doi.org/10.1109/adprl.2009.4927531","mag":"2168809087"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2009.4927531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","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/A5013021251","display_name":"Eugene A. Feinberg","orcid":"https://orcid.org/0000-0002-8263-0772"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eugene A. Feinberg","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Stony Brook University, Stony Brook, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013021251"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":0.7654,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79324972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"36","issue":null,"first_page":"96","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9955000281333923,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9955000281333923,"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"}},{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9447000026702881,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9381999969482422,"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":0.8662904500961304},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7592688202857971},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.693648099899292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6672408580780029},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.566742479801178},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5460706353187561},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5122320055961609},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5038534998893738},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.44779467582702637},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23652449250221252},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18460512161254883},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11752727627754211}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8662904500961304},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7592688202857971},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.693648099899292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6672408580780029},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.566742479801178},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5460706353187561},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5122320055961609},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5038534998893738},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.44779467582702637},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23652449250221252},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18460512161254883},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11752727627754211},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2009.4927531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W23471683","https://openalex.org/W1518931405","https://openalex.org/W1991591460","https://openalex.org/W1999680158","https://openalex.org/W2001139238","https://openalex.org/W2007881136","https://openalex.org/W2012045703","https://openalex.org/W2022585556","https://openalex.org/W2046359489","https://openalex.org/W2047485015","https://openalex.org/W2076812113","https://openalex.org/W2089363577","https://openalex.org/W2123649906","https://openalex.org/W2126534522","https://openalex.org/W2150757233","https://openalex.org/W2160690679","https://openalex.org/W4239243912","https://openalex.org/W6630965284","https://openalex.org/W7029993674"],"related_works":["https://openalex.org/W4231775656","https://openalex.org/W1660242800","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"This":[0],"paper":[1],"deals":[2],"with":[3,19,27],"computation":[4],"of":[5],"optimal":[6,42],"nonrandomized":[7,43],"nonstationary":[8],"policies":[9,13,44],"and":[10,22,30],"mixed":[11],"stationary":[12],"for":[14,40,49],"average-reward":[15],"Markov":[16],"decision":[17],"processes":[18],"multiple":[20],"criteria":[21],"constraints.":[23],"We":[24],"consider":[25],"problems":[26],"finite":[28],"state":[29],"action":[31],"sets":[32],"satisfying":[33],"the":[34],"unichain":[35],"condition.":[36],"The":[37],"described":[38],"procedure":[39],"computing":[41],"can":[45],"also":[46],"be":[47],"used":[48],"adaptive":[50],"control":[51],"problems.":[52]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}