{"id":"https://openalex.org/W1564711114","doi":"https://doi.org/10.1023/a:1007686309208","title":"A Study of Reinforcement Learning in the Continuous Case by the Means of Viscosity Solutions","display_name":"A Study of Reinforcement Learning in the Continuous Case by the Means of Viscosity Solutions","publication_year":2000,"publication_date":"2000-09-01","ids":{"openalex":"https://openalex.org/W1564711114","doi":"https://doi.org/10.1023/a:1007686309208","mag":"1564711114"},"language":"en","primary_location":{"id":"doi:10.1023/a:1007686309208","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1007686309208","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1007686309208.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1023/A:1007686309208.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006533777","display_name":"R\u00e9mi Munos","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"R\u00e9mi Munos","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, 15213, USA","Carnegie Mellon University, Robotics Institute, Pittsburgh, PA 15213, USA.  munos@cs.cmu.edu"],"affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, 15213, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Robotics Institute, Pittsburgh, PA 15213, USA.  munos@cs.cmu.edu","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5006533777"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":6.9987,"has_fulltext":true,"cited_by_count":75,"citation_normalized_percentile":{"value":0.96679315,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"40","issue":"3","first_page":"265","last_page":"299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9969000220298767,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9842000007629395,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.953652024269104},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.7225912809371948},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6808566451072693},{"id":"https://openalex.org/keywords/viscosity-solution","display_name":"Viscosity solution","score":0.6485113501548767},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5244113206863403},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5211513042449951},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5083293318748474},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.499767541885376},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42791682481765747},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4124714732170105},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3527522683143616},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.296828031539917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.19228816032409668}],"concepts":[{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.953652024269104},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7225912809371948},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6808566451072693},{"id":"https://openalex.org/C88731125","wikidata":"https://www.wikidata.org/wiki/Q7935676","display_name":"Viscosity solution","level":2,"score":0.6485113501548767},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5244113206863403},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5211513042449951},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5083293318748474},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.499767541885376},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42791682481765747},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4124714732170105},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3527522683143616},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.296828031539917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.19228816032409668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","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":1,"locations":[{"id":"doi:10.1023/a:1007686309208","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1007686309208","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1007686309208.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1023/a:1007686309208","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1007686309208","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1007686309208.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1564711114.pdf","grobid_xml":"https://content.openalex.org/works/W1564711114.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W20823384","https://openalex.org/W101787250","https://openalex.org/W111328409","https://openalex.org/W185726777","https://openalex.org/W1494474274","https://openalex.org/W1501482654","https://openalex.org/W1505284970","https://openalex.org/W1545148916","https://openalex.org/W1547105496","https://openalex.org/W1551593752","https://openalex.org/W1558902221","https://openalex.org/W1576452626","https://openalex.org/W1583833196","https://openalex.org/W1583902426","https://openalex.org/W1587799944","https://openalex.org/W1595483645","https://openalex.org/W1646707810","https://openalex.org/W1806564464","https://openalex.org/W1964377184","https://openalex.org/W1966195676","https://openalex.org/W1979071892","https://openalex.org/W1984482772","https://openalex.org/W2015740317","https://openalex.org/W2022384521","https://openalex.org/W2032316144","https://openalex.org/W2042112368","https://openalex.org/W2051269406","https://openalex.org/W2052520551","https://openalex.org/W2077883650","https://openalex.org/W2091565802","https://openalex.org/W2100644648","https://openalex.org/W2107726111","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2124175081","https://openalex.org/W2125074935","https://openalex.org/W2125510930","https://openalex.org/W2128281152","https://openalex.org/W2128777402","https://openalex.org/W2130746277","https://openalex.org/W2135651599","https://openalex.org/W2142377262","https://openalex.org/W2142409110","https://openalex.org/W2142592520","https://openalex.org/W2152704022","https://openalex.org/W2166356462","https://openalex.org/W2177195156","https://openalex.org/W2209557103","https://openalex.org/W2334591577","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W2542648826","https://openalex.org/W2749408143","https://openalex.org/W2761241455","https://openalex.org/W3206777520","https://openalex.org/W4230563027","https://openalex.org/W4231226883","https://openalex.org/W4240136462","https://openalex.org/W4297940609","https://openalex.org/W4298023569","https://openalex.org/W4302367620","https://openalex.org/W4307347247","https://openalex.org/W6634528131","https://openalex.org/W6635231448","https://openalex.org/W6646288407","https://openalex.org/W6656072165","https://openalex.org/W6676007687","https://openalex.org/W6678900246","https://openalex.org/W6704298589"],"related_works":["https://openalex.org/W2032834442","https://openalex.org/W1654696814","https://openalex.org/W3153900688","https://openalex.org/W4297940580","https://openalex.org/W4297409026","https://openalex.org/W2115544975","https://openalex.org/W1992466143","https://openalex.org/W1701657796","https://openalex.org/W2358967034","https://openalex.org/W2490159976"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2016-06-24T00:00:00"}