{"id":"https://openalex.org/W3017031890","doi":"https://doi.org/10.5555/2567709.2502618","title":"Performance bounds for \u03bb policy iteration and application to the game of Tetris","display_name":"Performance bounds for \u03bb policy iteration and application to the game of Tetris","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W3017031890","doi":"https://doi.org/10.5555/2567709.2502618","mag":"3017031890"},"language":"en","primary_location":{"id":"mag:3017031890","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/2567709.2502618","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research","raw_type":null},"type":"article","indexed_in":[],"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/A5071786100","display_name":"ScherrerBruno","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"ScherrerBruno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5071786100"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32230039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9807999730110168,"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":0.9807999730110168,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9412999749183655,"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/T10991","display_name":"Game Theory and Voting Systems","score":0.9204999804496765,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5373526811599731},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45253121852874756},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.4152318239212036},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3739832043647766},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34862804412841797},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3312798738479614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5373526811599731},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45253121852874756},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.4152318239212036},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3739832043647766},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34862804412841797},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3312798738479614}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3017031890","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/2567709.2502618","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Journal of Machine Learning Research","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2153947321","https://openalex.org/W1511927616","https://openalex.org/W1548889916","https://openalex.org/W3198564127","https://openalex.org/W2913022628","https://openalex.org/W3144388779","https://openalex.org/W2075754841","https://openalex.org/W2465145931","https://openalex.org/W3144437855","https://openalex.org/W2993527038","https://openalex.org/W1986055140","https://openalex.org/W2150617783","https://openalex.org/W2101748387","https://openalex.org/W2489939061","https://openalex.org/W2155580065","https://openalex.org/W2121816508","https://openalex.org/W2211193316","https://openalex.org/W1976275358","https://openalex.org/W3090442079","https://openalex.org/W2902806543"],"abstract_inverted_index":{"We":[0,19],"consider":[1],"the":[2,21],"discrete-time":[3],"infinite-horizon":[4],"optimal":[5],"control":[6],"problem":[7],"formalized":[8],"by":[9],"Markov":[10],"decision":[11],"processes":[12],"(Puterman,":[13],"1994;":[14],"Bertsekas":[15,24],"and":[16],"Tsitsiklis,":[17],"1996).":[18],"revisit":[20],"work":[22],"of":[23],"and...":[25]},"counts_by_year":[],"updated_date":"2025-10-10T17:16:08.811792","created_date":"2025-10-10T00:00:00"}