{"id":"https://openalex.org/W2097562045","doi":"https://doi.org/10.1109/isit.2004.1365505","title":"PAC learning for markov decision processes and dynamic games","display_name":"PAC learning for markov decision processes and dynamic games","publication_year":2004,"publication_date":"2004-12-23","ids":{"openalex":"https://openalex.org/W2097562045","doi":"https://doi.org/10.1109/isit.2004.1365505","mag":"2097562045"},"language":"en","primary_location":{"id":"doi:10.1109/isit.2004.1365505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2004.1365505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Symposium onInformation Theory, 2004. ISIT 2004. Proceedings.","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/A5002082998","display_name":"Rahul Jain","orcid":"https://orcid.org/0000-0003-3786-8682"},"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":"Rahul Jain","raw_affiliation_strings":["EECS Department, University of California, Berkeley, CA, USA","EECS Dept., California Univ., Berkeley, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"EECS Department, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"EECS Dept., California Univ., Berkeley, CA, USA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040150415","display_name":"Pravin Varaiya","orcid":"https://orcid.org/0000-0002-1900-9932"},"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":"P. Varaiya","raw_affiliation_strings":["EECS Department, University of California, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"EECS Department, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002082998"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1193982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"468","last_page":"468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9399999976158142,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9399999976158142,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.930400013923645,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9136000275611877,"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":0.9045023918151855},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6974779367446899},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.6863018870353699},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6342508792877197},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.609748125076294},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5878596901893616},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5465909242630005},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5373607277870178},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5276992321014404},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.46966636180877686},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41009721159935},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3928608298301697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3429262638092041},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3115761876106262},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2547822892665863},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09196662902832031}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.9045023918151855},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6974779367446899},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6863018870353699},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6342508792877197},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.609748125076294},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5878596901893616},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5465909242630005},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5373607277870178},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5276992321014404},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.46966636180877686},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41009721159935},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3928608298301697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3429262638092041},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3115761876106262},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2547822892665863},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09196662902832031},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isit.2004.1365505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2004.1365505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Symposium onInformation Theory, 2004. ISIT 2004. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.130.9239","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.130.9239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wow.eecs.berkeley.edu/~rjain/papers/isit04final.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2156021013","https://openalex.org/W2016648086","https://openalex.org/W4399157305","https://openalex.org/W3105579180","https://openalex.org/W1574958246"],"abstract_inverted_index":{"We":[0,18,33],"extend":[1],"the":[2],"probably":[3],"approximately":[4],"correct":[5],"(PAC)":[6],"model":[7],"of":[8,29,47],"learning":[9],"to":[10],"Markov":[11,41],"decision":[12],"processes":[13],"(MDPs)":[14],"and":[15],"dynamic":[16],"games.":[17],"obtain":[19,35],"simulation-based":[20],"uniform":[21,36],"sample":[22,37],"complexity":[23,38],"bounds":[24],"for":[25,40],"value":[26],"function":[27],"estimates":[28],"discounted":[30],"reward":[31],"MDPs.":[32],"also":[34],"results":[39],"games":[42],"with":[43],"a":[44],"finite":[45],"number":[46],"players.":[48]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}