{"id":"https://openalex.org/W2155355065","doi":"https://doi.org/10.1007/978-3-540-72927-3_20","title":"Bounded Parameter Markov Decision Processes with Average Reward Criterion","display_name":"Bounded Parameter Markov Decision Processes with Average Reward Criterion","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2155355065","doi":"https://doi.org/10.1007/978-3-540-72927-3_20","mag":"2155355065"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-72927-3_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-72927-3_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5051918150","display_name":"Ambuj Tewari","orcid":"https://orcid.org/0000-0001-6969-7844"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ambuj Tewari","raw_affiliation_strings":["University of California, Berkeley, Division of Computer Science, 544 Soda Hall # 1776, Berkeley, CA 94720-1776, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Division of Computer Science, 544 Soda Hall # 1776, Berkeley, CA 94720-1776, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030261391","display_name":"Peter L. Bartlett","orcid":"https://orcid.org/0000-0002-8760-3140"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter L. Bartlett","raw_affiliation_strings":["University of California, Berkeley, Division of Computer Science and Department of Statistics, 387 Soda Hall # 1776, Berkeley, CA 94720-1776, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Division of Computer Science and Department of Statistics, 387 Soda Hall # 1776, Berkeley, CA 94720-1776, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051918150"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":3.6435,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94284113,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"263","last_page":"277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9980000257492065,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9970999956130981,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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":0.860203742980957},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.7160294055938721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6745142340660095},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.580413818359375},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5802572965621948},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5531335473060608},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5091339945793152},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4484163522720337},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.42754024267196655},{"id":"https://openalex.org/keywords/decision-process","display_name":"Decision process","score":0.4210221767425537},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3732761740684509},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32175320386886597},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12059110403060913},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10401654243469238},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.09187930822372437},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.05423852801322937}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.860203742980957},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.7160294055938721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6745142340660095},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.580413818359375},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5802572965621948},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5531335473060608},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5091339945793152},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4484163522720337},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42754024267196655},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.4210221767425537},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3732761740684509},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32175320386886597},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12059110403060913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10401654243469238},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.09187930822372437},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.05423852801322937},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-540-72927-3_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-72927-3_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.152.1444","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.152.1444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eecs.berkeley.edu/~ambuj/research/tewari07bounded.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.714.9460","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.714.9460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dept.stat.lsa.umich.edu/%7Etewaria/research/tewari07bounded.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W580976455","https://openalex.org/W1505937442","https://openalex.org/W1544193923","https://openalex.org/W1965878388","https://openalex.org/W1988217924","https://openalex.org/W1998376807","https://openalex.org/W2082691056","https://openalex.org/W2097931172","https://openalex.org/W2098432798","https://openalex.org/W2129620190","https://openalex.org/W2999905431","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2149476049","https://openalex.org/W199494732","https://openalex.org/W2048124834","https://openalex.org/W1970298188","https://openalex.org/W60247044","https://openalex.org/W2530417802","https://openalex.org/W3013781205","https://openalex.org/W161694800","https://openalex.org/W2092187522","https://openalex.org/W2322890683"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}