{"id":"https://openalex.org/W2152670157","doi":"https://doi.org/10.5555/1390681.1442787","title":"Value Function Based Reinforcement Learning in Changing Markovian Environments","display_name":"Value Function Based Reinforcement Learning in Changing Markovian Environments","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2152670157","doi":"https://doi.org/10.5555/1390681.1442787","mag":"2152670157"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.210.6946","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.210.6946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jmlr.org/papers/volume9/csaji08a/csaji08a.pdf","raw_type":"text"},"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/A5016151972","display_name":"Bal\u00e1zs Csan\u00e1d Cs\u00e1ji","orcid":"https://orcid.org/0000-0001-7079-8343"},"institutions":[{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Bal\u00e1zs Csan\u00e1d Cs\u00e1ji","raw_affiliation_strings":["Hungarian Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0001-7079-8343","affiliations":[{"raw_affiliation_string":"Hungarian Academy of Sciences","institution_ids":["https://openalex.org/I7597260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049960953","display_name":"L\u00e1szl\u00f3 Monostori","orcid":"https://orcid.org/0000-0001-8692-8640"},"institutions":[{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"L\u00e1szl\u00f3 Monostori","raw_affiliation_strings":["Hungarian Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0001-8692-8640","affiliations":[{"raw_affiliation_string":"Hungarian Academy of Sciences","institution_ids":["https://openalex.org/I7597260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7597260"],"apc_list":null,"apc_paid":null,"fwci":5.3687,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.95270506,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"9","issue":"54","first_page":"1679","last_page":"1709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9660000205039978,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.8910307884216309},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.8365705013275146},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8264546394348145},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.6766705513000488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6284147500991821},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5950412750244141},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5605016946792603},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.553943395614624},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.552954912185669},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5473702549934387},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5099955797195435},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.48965317010879517},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.48800817131996155},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.44393327832221985},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4316445589065552},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.41567161679267883},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3248337209224701},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31245726346969604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23003917932510376},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1334286630153656},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07635745406150818}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8910307884216309},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.8365705013275146},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8264546394348145},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.6766705513000488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6284147500991821},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5950412750244141},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5605016946792603},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.553943395614624},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.552954912185669},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5473702549934387},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5099955797195435},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.48965317010879517},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.48800817131996155},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.44393327832221985},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4316445589065552},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41567161679267883},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3248337209224701},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31245726346969604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23003917932510376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1334286630153656},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07635745406150818},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.210.6946","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.210.6946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jmlr.org/papers/volume9/csaji08a/csaji08a.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.sztaki.hu:5344","is_oa":false,"landing_page_url":"http://eprints.sztaki.hu/5344/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401907","display_name":"SZTAKI Publication Repository (Hungarian Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I7597260","host_organization_name":"Hungarian Academy of Sciences","host_organization_lineage":["https://openalex.org/I7597260"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"ISI Article"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/29308","is_oa":false,"landing_page_url":"http://hdl.handle.net/11343/29308","pdf_url":null,"source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"mag:2152670157","is_oa":false,"landing_page_url":"http://sztaki.hu/~csaji/csaji-jmlr-2008.pdf","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","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"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","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W199168817","https://openalex.org/W1487586669","https://openalex.org/W1515851193","https://openalex.org/W1516418405","https://openalex.org/W1552132860","https://openalex.org/W1576452626","https://openalex.org/W1777097917","https://openalex.org/W2013614847","https://openalex.org/W2071223301","https://openalex.org/W2089415692","https://openalex.org/W2098432798","https://openalex.org/W2118686230","https://openalex.org/W2119101452","https://openalex.org/W2122967269","https://openalex.org/W2132514348","https://openalex.org/W2155027007","https://openalex.org/W2169022337","https://openalex.org/W2179771332","https://openalex.org/W2408727253","https://openalex.org/W2489939061","https://openalex.org/W2911283634","https://openalex.org/W2914656440"],"related_works":["https://openalex.org/W2121863487","https://openalex.org/W3105579180","https://openalex.org/W2914656440","https://openalex.org/W2119567691","https://openalex.org/W1576452626","https://openalex.org/W2994143999","https://openalex.org/W2552244163","https://openalex.org/W1996627310","https://openalex.org/W2122689259","https://openalex.org/W2963911212","https://openalex.org/W2151661095","https://openalex.org/W3147478359","https://openalex.org/W1493119321","https://openalex.org/W2733397824","https://openalex.org/W3101874568","https://openalex.org/W2098432798","https://openalex.org/W3025837736","https://openalex.org/W2962901215","https://openalex.org/W3013054151","https://openalex.org/W288152395"],"abstract_inverted_index":{"1679":[0]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}