{"id":"https://openalex.org/W1531900088","doi":"https://doi.org/10.1023/a:1017988514716","title":"Continuous-Action Q-Learning","display_name":"Continuous-Action Q-Learning","publication_year":2002,"publication_date":"2002-11-01","ids":{"openalex":"https://openalex.org/W1531900088","doi":"https://doi.org/10.1023/a:1017988514716","mag":"1531900088"},"language":"en","primary_location":{"id":"doi:10.1023/a:1017988514716","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1017988514716","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1017988514716.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:1017988514716.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050363894","display_name":"Jos\u00e9 del R. Mill\u00e1n","orcid":"https://orcid.org/0000-0001-5819-1522"},"institutions":[{"id":"https://openalex.org/I4210118689","display_name":"Joint Research Centre","ror":"https://ror.org/02qezmz13","country_code":"IT","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288","https://openalex.org/I4210118689","https://openalex.org/I4210161702"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Jos\u00e9 del R. Mill\u00e1n","raw_affiliation_strings":["Joint Research Centre, European Commission, 21020, Ispra (VA), Italy","Joint Research Centre, European Commission, 21020 Ispra (VA), Italy. jose.millan@jrc.it (http://sta.jrc.it/sba/staff/jose.htm)#TAB#"],"affiliations":[{"raw_affiliation_string":"Joint Research Centre, European Commission, 21020, Ispra (VA), Italy","institution_ids":["https://openalex.org/I4210118689"]},{"raw_affiliation_string":"Joint Research Centre, European Commission, 21020 Ispra (VA), Italy. jose.millan@jrc.it (http://sta.jrc.it/sba/staff/jose.htm)#TAB#","institution_ids":["https://openalex.org/I4210118689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029194561","display_name":"Daniele Posenato","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118689","display_name":"Joint Research Centre","ror":"https://ror.org/02qezmz13","country_code":"IT","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288","https://openalex.org/I4210118689","https://openalex.org/I4210161702"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Daniele Posenato","raw_affiliation_strings":["Joint Research Centre, European Commission, 21020, Ispra (VA), Italy","Joint Research Centre, European Commission, 21020 Ispra (VA), Italy. daniele.posenato@jrc.it#TAB#"],"affiliations":[{"raw_affiliation_string":"Joint Research Centre, European Commission, 21020, Ispra (VA), Italy","institution_ids":["https://openalex.org/I4210118689"]},{"raw_affiliation_string":"Joint Research Centre, European Commission, 21020 Ispra (VA), Italy. daniele.posenato@jrc.it#TAB#","institution_ids":["https://openalex.org/I4210118689"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051683172","display_name":"\u00c9ric Dedieu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118689","display_name":"Joint Research Centre","ror":"https://ror.org/02qezmz13","country_code":"IT","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288","https://openalex.org/I4210118689","https://openalex.org/I4210161702"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Eric Dedieu","raw_affiliation_strings":["Joint Research Centre, European Commission, 21020, Ispra (VA), Italy","Joint Research Centre, European Commission, 21020 Ispra (VA), Italy. eric.dedieu@jrc.it#TAB#"],"affiliations":[{"raw_affiliation_string":"Joint Research Centre, European Commission, 21020, Ispra (VA), Italy","institution_ids":["https://openalex.org/I4210118689"]},{"raw_affiliation_string":"Joint Research Centre, European Commission, 21020 Ispra (VA), Italy. eric.dedieu@jrc.it#TAB#","institution_ids":["https://openalex.org/I4210118689"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050363894"],"corresponding_institution_ids":["https://openalex.org/I4210118689"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":5.1256,"has_fulltext":true,"cited_by_count":122,"citation_normalized_percentile":{"value":0.96093621,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"49","issue":"2-3","first_page":"247","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9858999848365784,"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/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.9664000272750854,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/artificial-intelligence","display_name":"Artificial intelligence","score":0.5931661128997803},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5925862193107605},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5469146966934204},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5222674012184143},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.49125903844833374},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4905976355075836},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44818615913391113},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4413278102874756},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42566633224487305},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42233455181121826},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.37768101692199707},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.2957673668861389},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.19578805565834045},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10429412126541138},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.10203379392623901}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5931661128997803},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5925862193107605},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5469146966934204},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5222674012184143},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.49125903844833374},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4905976355075836},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44818615913391113},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4413278102874756},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42566633224487305},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42233455181121826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37768101692199707},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2957673668861389},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.19578805565834045},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10429412126541138},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10203379392623901},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1023/a:1017988514716","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1017988514716","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1017988514716.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:1017988514716","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1017988514716","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1017988514716.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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1531900088.pdf","grobid_xml":"https://content.openalex.org/works/W1531900088.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W65193931","https://openalex.org/W140176866","https://openalex.org/W1515851193","https://openalex.org/W1549353711","https://openalex.org/W1646707810","https://openalex.org/W1679913846","https://openalex.org/W1969420452","https://openalex.org/W2028357975","https://openalex.org/W2059039791","https://openalex.org/W2063883439","https://openalex.org/W2091565802","https://openalex.org/W2100677568","https://openalex.org/W2101915445","https://openalex.org/W2105560683","https://openalex.org/W2113913482","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2127290018","https://openalex.org/W2138754805","https://openalex.org/W2141559645","https://openalex.org/W2154549708","https://openalex.org/W2156666447","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W4214717370","https://openalex.org/W4237222446","https://openalex.org/W4252939763","https://openalex.org/W4253978526","https://openalex.org/W4254755460","https://openalex.org/W4256160650","https://openalex.org/W6602690695","https://openalex.org/W6677916085","https://openalex.org/W6680294583","https://openalex.org/W6780394890"],"related_works":["https://openalex.org/W4233452137","https://openalex.org/W4254857216","https://openalex.org/W405964254","https://openalex.org/W2728224919","https://openalex.org/W2045758229","https://openalex.org/W4231626925","https://openalex.org/W2962829499","https://openalex.org/W2951521427","https://openalex.org/W2398963826","https://openalex.org/W1985059659"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
