{"id":"https://openalex.org/W1603605173","doi":"https://doi.org/10.1007/978-3-642-02478-8_73","title":"Two Steps Reinforcement Learning in Continuous Reinforcement Learning Tasks","display_name":"Two Steps Reinforcement Learning in Continuous Reinforcement Learning Tasks","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1603605173","doi":"https://doi.org/10.1007/978-3-642-02478-8_73","mag":"1603605173"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-02478-8_73","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-02478-8_73","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","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/A5003933377","display_name":"Iv\u00e1n L\u00f3pez-Bueno","orcid":null},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Iv\u00e1n L\u00f3pez-Bueno","raw_affiliation_strings":["Universidad Carlos III de Madrid, Avda. de la Universidad 30, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Carlos III de Madrid, Avda. de la Universidad 30, Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645872","display_name":"Javier Garc\u00eda","orcid":"https://orcid.org/0000-0002-5638-5240"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Garc\u00eda","raw_affiliation_strings":["Universidad Carlos III de Madrid, Avda. de la Universidad 30, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Carlos III de Madrid, Avda. de la Universidad 30, Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004703726","display_name":"Fernando Fern\u00e1ndez","orcid":"https://orcid.org/0000-0003-3801-6801"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Fernando Fern\u00e1ndez","raw_affiliation_strings":["Universidad Carlos III de Madrid, Avda. de la Universidad 30, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Carlos III de Madrid, Avda. de la Universidad 30, Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I50357001"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"577","last_page":"584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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":0.9968000054359436,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9966999888420105,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9003705978393555},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.8036362528800964},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.754028856754303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5461865067481995},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.5190554261207581},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.49960899353027344},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4944305419921875},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4670252799987793},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42854610085487366},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4280073940753937},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4117233157157898},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16489815711975098},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1411154866218567}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9003705978393555},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.8036362528800964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754028856754303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5461865067481995},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5190554261207581},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.49960899353027344},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4944305419921875},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4670252799987793},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42854610085487366},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4280073940753937},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4117233157157898},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16489815711975098},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1411154866218567},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-02478-8_73","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-02478-8_73","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.650.4467","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.650.4467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://scalab.uc3m.es/~ffernand/papers/iwann09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1510432098","https://openalex.org/W1515851193","https://openalex.org/W1528113134","https://openalex.org/W1552830313","https://openalex.org/W1570448133","https://openalex.org/W2104641222","https://openalex.org/W2107726111","https://openalex.org/W2114882146","https://openalex.org/W2115951219","https://openalex.org/W2121863487","https://openalex.org/W2125074935","https://openalex.org/W2341171179","https://openalex.org/W2966207845","https://openalex.org/W4214717370","https://openalex.org/W4235899661"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W4225571923","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
