{"id":"https://openalex.org/W1748709110","doi":"https://doi.org/10.1007/3-540-44581-1_41","title":"Bounds on Sample Size for Policy Evaluation in Markov Environments","display_name":"Bounds on Sample Size for Policy Evaluation in Markov Environments","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W1748709110","doi":"https://doi.org/10.1007/3-540-44581-1_41","mag":"1748709110"},"language":"en","primary_location":{"id":"doi:10.1007/3-540-44581-1_41","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-44581-1_41","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":"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/A5091208273","display_name":"Leonid Peshkin","orcid":"https://orcid.org/0000-0002-6420-848X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonid Peshkin","raw_affiliation_strings":["MIT Artificial Intelligence Laboratory, 545 Technology Square, Cambridge, MA, 02139"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Artificial Intelligence Laboratory, 545 Technology Square, Cambridge, MA, 02139","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101494951","display_name":"Sayan Mukherjee","orcid":"https://orcid.org/0000-0001-8838-0455"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sayan Mukherjee","raw_affiliation_strings":["MIT Artificial Intelligence Laboratory, 545 Technology Square, Cambridge, MA, 02139"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Artificial Intelligence Laboratory, 545 Technology Square, Cambridge, MA, 02139","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"616","last_page":"629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9915000200271606,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9718999862670898,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8207883834838867},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7756518125534058},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.694793701171875},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6798202395439148},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5421567559242249},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5044959783554077},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4697665870189667},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46947821974754333},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.46901601552963257},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.43006038665771484},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41614818572998047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2536005973815918},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23146948218345642},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11216729879379272},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10790202021598816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207883834838867},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7756518125534058},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.694793701171875},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6798202395439148},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5421567559242249},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5044959783554077},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4697665870189667},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46947821974754333},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.46901601552963257},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43006038665771484},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41614818572998047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2536005973815918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23146948218345642},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11216729879379272},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10790202021598816},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/3-540-44581-1_41","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-44581-1_41","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1509294466","https://openalex.org/W1514587017","https://openalex.org/W1518095400","https://openalex.org/W1564684328","https://openalex.org/W1590759229","https://openalex.org/W1596364083","https://openalex.org/W1606274310","https://openalex.org/W1640774615","https://openalex.org/W1657542410","https://openalex.org/W1998255116","https://openalex.org/W2010029425","https://openalex.org/W2022637125","https://openalex.org/W2032100464","https://openalex.org/W2043191154","https://openalex.org/W2055598786","https://openalex.org/W2063471322","https://openalex.org/W2084544490","https://openalex.org/W2087018957","https://openalex.org/W2107726111","https://openalex.org/W2119717200","https://openalex.org/W2129113961","https://openalex.org/W2147632348","https://openalex.org/W2148603752","https://openalex.org/W2156909104","https://openalex.org/W2161521419","https://openalex.org/W2170586091","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W2767443199","https://openalex.org/W2989661724","https://openalex.org/W4233358567","https://openalex.org/W4292025355","https://openalex.org/W6685176817"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W4225269853","https://openalex.org/W3168977894"],"abstract_inverted_index":null,"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}