{"id":"https://openalex.org/W2167650507","doi":"https://doi.org/10.1145/1553374.1553502","title":"Optimistic initialization and greediness lead to polynomial time learning in factored MDPs","display_name":"Optimistic initialization and greediness lead to polynomial time learning in factored MDPs","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W2167650507","doi":"https://doi.org/10.1145/1553374.1553502","mag":"2167650507"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553502","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine 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/A5053869649","display_name":"Istv\u00e1n Szita","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Istv\u00e1n Szita","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066832439","display_name":"Andr\u00e1s L\u00f6rincz","orcid":"https://orcid.org/0000-0002-1280-3447"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Andr\u00e1s L\u0151rincz","raw_affiliation_strings":["E\u00f6tv\u00f6s Lor\u00e1nd University, Hungary"],"affiliations":[{"raw_affiliation_string":"E\u00f6tv\u00f6s Lor\u00e1nd University, Hungary","institution_ids":["https://openalex.org/I106118109"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053869649"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":3.1614,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.9254791,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1001","last_page":"1008"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10142","display_name":"Formal Methods in Verification","score":0.9868000149726868,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9866999983787537,"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/initialization","display_name":"Initialization","score":0.8086618781089783},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.720072865486145},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7051267027854919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6333385109901428},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5774306654930115},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.5367060899734497},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.4816654920578003},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4191907048225403},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3924177885055542},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2709767818450928},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2599870562553406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24395152926445007},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14350587129592896}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8086618781089783},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.720072865486145},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7051267027854919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6333385109901428},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5774306654930115},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.5367060899734497},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.4816654920578003},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4191907048225403},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3924177885055542},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2709767818450928},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2599870562553406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24395152926445007},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14350587129592896},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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":3,"locations":[{"id":"doi:10.1145/1553374.1553502","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.7417","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.7417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.mcgill.ca/~icml2009/papers/290.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.315.2444","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.315.2444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/0904.3352v1.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G7407463774","display_name":null,"funder_award_id":"43261","funder_id":"https://openalex.org/F4320334962","funder_display_name":"Sixth Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334962","display_name":"Sixth Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1502893368","https://openalex.org/W1515399492","https://openalex.org/W1537180453","https://openalex.org/W1554015367","https://openalex.org/W1650504995","https://openalex.org/W1997477668","https://openalex.org/W2082691056","https://openalex.org/W2129679414","https://openalex.org/W2144744117","https://openalex.org/W2149896419","https://openalex.org/W2154347416","https://openalex.org/W2161966552","https://openalex.org/W2167650507","https://openalex.org/W2489939061","https://openalex.org/W3004360271","https://openalex.org/W3023407077","https://openalex.org/W3103882218","https://openalex.org/W3170719636","https://openalex.org/W6630339688","https://openalex.org/W6636774213","https://openalex.org/W6682099972"],"related_works":["https://openalex.org/W3204184292","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/W3168977894"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"an":[5,25],"algorithm":[6,51,107,119],"for":[7],"polynomial-time":[8],"reinforcement":[9],"learning":[10],"in":[11,31,97],"factored":[12,18],"Markov":[13],"decision":[14],"processes":[15],"(FMDPs).":[16],"The":[17,46],"optimistic":[19],"initial":[20],"model":[21,27,55],"(FOIM)":[22],"algorithm,":[23],"maintains":[24],"empirical":[26],"of":[28,49,72,80,93,105],"the":[29,50,54,69,78,83,91,102,106,117],"FMDP":[30],"a":[32,38],"conventional":[33],"way,":[34],"and":[35],"always":[36],"follows":[37],"greedy":[39],"policy":[40],"with":[41,62,120],"respect":[42,89],"to":[43,68,90],"its":[44],"model.":[45],"only":[47],"trick":[48],"is":[52,56,95,116],"that":[53,61],"initialized":[57],"optimistically.":[58],"We":[59],"prove":[60],"suitable":[63],"initialization":[64],"(i)":[65],"FOIM":[66,115],"converges":[67],"fixed":[70],"point":[71],"approximate":[73],"value":[74],"iteration":[75],"(AVI);":[76],"(ii)":[77],"number":[79],"steps":[81],"when":[82],"agent":[84],"makes":[85],"non-near-optimal":[86],"decisions":[87],"(with":[88],"solution":[92],"AVI)":[94],"polynomial":[96],"all":[98],"relevant":[99],"quantities;":[100],"(iii)":[101],"per-step":[103],"costs":[104],"are":[108],"also":[109],"polynomial.":[110],"To":[111],"our":[112],"best":[113],"knowledge,":[114],"first":[118],"these":[121],"properties.":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}