{"id":"https://openalex.org/W186489565","doi":"https://doi.org/10.1007/978-0-387-09695-7_15","title":"Batch Reinforcement Learning for Controlling a Mobile Wheeled Pendulum Robot","display_name":"Batch Reinforcement Learning for Controlling a Mobile Wheeled Pendulum Robot","publication_year":2008,"publication_date":"2008-08-19","ids":{"openalex":"https://openalex.org/W186489565","doi":"https://doi.org/10.1007/978-0-387-09695-7_15","mag":"186489565"},"language":"en","primary_location":{"id":"doi:10.1007/978-0-387-09695-7_15","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-0-387-09695-7_15","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-0-387-09695-7_15.pdf","source":{"id":"https://openalex.org/S4210175514","display_name":"IFIP International Federation for Information Processing/IFIP","issn_l":"1571-5736","issn":["1571-5736","1861-2288"],"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":"IFIP \u2013 The International Federation for Information Processing","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007%2F978-0-387-09695-7_15.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060263666","display_name":"Andrea Bonarini","orcid":"https://orcid.org/0000-0002-4880-4521"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Bonarini","raw_affiliation_strings":["Dept. of Electronics and Information, Politecnico di Milano, Milan, Italy","Department of Electronics and Information , Politecnico di Milano , Milan , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Information, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Department of Electronics and Information , Politecnico di Milano , Milan , Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005038232","display_name":"Claudio Giovanni Caccia","orcid":null},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudio Caccia","raw_affiliation_strings":["Dept. of Informatics, Systems and Communication, Universit\u00e0 degli Studi di Milano \u2013 Bicocca, Milan, Italy","Universit\u00e0 degli Studi di Milano-Bicocca"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Informatics, Systems and Communication, Universit\u00e0 degli Studi di Milano \u2013 Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]},{"raw_affiliation_string":"Universit\u00e0 degli Studi di Milano-Bicocca","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014791481","display_name":"Alessandro Lazaric","orcid":"https://orcid.org/0000-0002-8970-413X"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Lazaric","raw_affiliation_strings":["Dept. of Electronics and Information, Politecnico di Milano, Milan, Italy","Department of Electronics and Information , Politecnico di Milano , Milan , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Information, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Department of Electronics and Information , Politecnico di Milano , Milan , Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017130830","display_name":"Marcello Restelli","orcid":"https://orcid.org/0000-0002-6322-1076"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcello Restelli","raw_affiliation_strings":["Dept. of Electronics and Information, Politecnico di Milano, Milan, Italy","Department of Electronics and Information , Politecnico di Milano , Milan , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Information, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Department of Electronics and Information , Politecnico di Milano , Milan , Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9930999875068665,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9837999939918518,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7634314298629761},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.7220208048820496},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.592420220375061},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5805065035820007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5764320492744446},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5700101852416992},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5311675667762756},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5268798470497131},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5147707462310791},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4980747699737549},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.48030251264572144},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.47459906339645386},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45351073145866394},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.44743508100509644},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4183926582336426},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3506906032562256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33977222442626953},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33904242515563965},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2542257308959961},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18141216039657593},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.07608598470687866}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7634314298629761},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.7220208048820496},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.592420220375061},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5805065035820007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5764320492744446},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5700101852416992},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5311675667762756},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5268798470497131},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5147707462310791},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4980747699737549},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.48030251264572144},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.47459906339645386},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45351073145866394},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.44743508100509644},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4183926582336426},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3506906032562256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33977222442626953},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33904242515563965},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2542257308959961},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18141216039657593},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.07608598470687866},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-0-387-09695-7_15","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-0-387-09695-7_15","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-0-387-09695-7_15.pdf","source":{"id":"https://openalex.org/S4210175514","display_name":"IFIP International Federation for Information Processing/IFIP","issn_l":"1571-5736","issn":["1571-5736","1861-2288"],"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":"IFIP \u2013 The International Federation for Information Processing","raw_type":"book-chapter"},{"id":"pmh:oai:re.public.polimi.it:11311/549210","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/549210","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1007/978-0-387-09695-7_15","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-0-387-09695-7_15","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-0-387-09695-7_15.pdf","source":{"id":"https://openalex.org/S4210175514","display_name":"IFIP International Federation for Information Processing/IFIP","issn_l":"1571-5736","issn":["1571-5736","1861-2288"],"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":"IFIP \u2013 The International Federation for Information Processing","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W186489565.pdf","grobid_xml":"https://content.openalex.org/works/W186489565.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W368409423","https://openalex.org/W599916913","https://openalex.org/W1506832649","https://openalex.org/W1550698229","https://openalex.org/W1582137406","https://openalex.org/W1646707810","https://openalex.org/W2076420009","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2313564472","https://openalex.org/W2432517183","https://openalex.org/W3004157836","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2775112436","https://openalex.org/W3326829","https://openalex.org/W2350013143","https://openalex.org/W3046172785","https://openalex.org/W2385948153","https://openalex.org/W2353814909","https://openalex.org/W2147778705","https://openalex.org/W2203843426","https://openalex.org/W2388509240","https://openalex.org/W2049369111"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
