{"id":"https://openalex.org/W2109102709","doi":null,"title":"Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods","display_name":"Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods","publication_year":2007,"publication_date":"2007-12-03","ids":{"openalex":"https://openalex.org/W2109102709","mag":"2109102709"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.188.7798","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.188.7798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sequel.futurs.inria.fr/lazaric/lazaric2008reinforcement.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"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/A5014791481","display_name":"Alessandro Lazaric","orcid":"https://orcid.org/0000-0002-8970-413X","observed_orcids":["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":["Department of Electronics and Information , Politecnico di Milano , Milan , Italy"],"raw_orcid":null,"affiliations":[{"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/A5017130830","display_name":"Marcello Restelli","orcid":"https://orcid.org/0000-0002-6322-1076","observed_orcids":["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":["Department of Electronics and Information , Politecnico di Milano , Milan , Italy"],"raw_orcid":"https://orcid.org/0000-0002-6322-1076","affiliations":[{"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/A5060263666","display_name":"Andrea Bonarini","orcid":"https://orcid.org/0000-0002-4880-4521","observed_orcids":["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":["Department of Electronics and Information , Politecnico di Milano , Milan , Italy"],"raw_orcid":"https://orcid.org/0000-0002-4880-4521","affiliations":[{"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":4.6543,"has_fulltext":false,"cited_by_count":114,"citation_normalized_percentile":{"value":0.94695188,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"20","issue":null,"first_page":"833","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.0,"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/reinforcement-learning","display_name":"reinforcement learning","score":0.847000002861023},{"id":"https://openalex.org/keywords/continuous-action-spaces","display_name":"continuous action spaces","score":0.9990000128746033},{"id":"https://openalex.org/keywords/actor-critic","display_name":"actor-critic","score":0.8640000224113464},{"id":"https://openalex.org/keywords/sequential-monte-carlo","display_name":"sequential Monte Carlo","score":0.8849999904632568},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"importance sampling","score":0.9559999704360962},{"id":"https://openalex.org/keywords/resampling","display_name":"resampling","score":0.9150000214576721},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.8159999847412109}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.867841899394989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6773554086685181},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.6649375557899475},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.6199317574501038},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5669560432434082},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5362716317176819},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5116715431213379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115752816200256},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48538410663604736},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4711310565471649},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4616372287273407},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44275978207588196},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4251896142959595},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4142061173915863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37295427918434143},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2756475508213043},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2379126250743866},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14017948508262634},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.188.7798","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.188.7798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sequel.futurs.inria.fr/lazaric/lazaric2008reinforcement.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.779","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://books.nips.cc/papers/files/nips20/NIPS2007_0959.pdf","raw_type":"text"},{"id":"pmh:oai:re.public.polimi.it:11311/539022","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/539022","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,"listed_in":[],"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"},{"id":"mag:2109102709","doi":null,"is_oa":false,"landing_page_url":"http://chercheurs.lille.inria.fr/~lazaric/Webpage/Publications_files/lazaric2008reinforcement.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1531900088","https://openalex.org/W1543217731","https://openalex.org/W1576452626","https://openalex.org/W2009303086","https://openalex.org/W2064480843","https://openalex.org/W2101539915","https://openalex.org/W2121863487","https://openalex.org/W2127107099","https://openalex.org/W2144366468","https://openalex.org/W2154549708","https://openalex.org/W2156737235","https://openalex.org/W2160279936","https://openalex.org/W2160337655","https://openalex.org/W2305205647","https://openalex.org/W2312609093"],"related_works":["https://openalex.org/W2101539915","https://openalex.org/W2786711334","https://openalex.org/W2268920910","https://openalex.org/W7014846787","https://openalex.org/W1585546346","https://openalex.org/W7099204643","https://openalex.org/W2181919496","https://openalex.org/W2158462832","https://openalex.org/W2386322474","https://openalex.org/W4406975827"],"abstract_inverted_index":{"Learning":[0,23],"in":[1,73,125,132],"real-world":[2],"domains":[3],"often":[4],"requires":[5],"to":[6,20,25,36,118],"deal":[7],"with":[8],"continuous":[9,26,37],"state":[10,27],"and":[11],"\\naction":[12],"spaces.":[13],"Although":[14],"many":[15],"solutions":[16],"have":[17],"been":[18,115],"proposed":[19,112],"apply":[21],"reinforcement":[22],"algorithms":[24,121],"problems,":[28],"the":[29,42,49,56,59,75,78,94,97,101,104,108],"same":[30],"techniques":[31],"can":[32],"be":[33],"hardly":[34],"extended":[35],"action":[38,61],"spaces,":[39],"where,":[40],"besides":[41],"computation":[43],"of":[44,48,58,77,96,137],"a":[45,52,69,133,139,142],"good":[46],"approximation":[47],"value":[50],"function,":[51],"fast":[53],"method":[54],"for":[55],"identification":[57],"highest-valued":[60],"is":[62,80,91],"needed.":[63],"In":[64],"this":[65,126],"paper,":[66,127],"we":[67,128],"propose":[68],"novel":[70],"actor-critic":[71],"approach":[72,113],"which":[74],"policy":[76],"actor":[79],"estimated":[81],"through":[82],"sequential":[83],"Monte":[84],"Carlo":[85],"methods.":[86],"The":[87],"importance":[88],"sampling":[89],"step":[90,106],"performed":[92],"on":[93],"basis":[95],"values":[98],"learned":[99],"by":[100],"critic,":[102],"while":[103],"resampling":[105],"modifies":[107],"actor\u2019s":[109],"policy.":[110],"\\nThe":[111],"has":[114],"empirically":[116],"compared":[117],"other":[119],"learning":[120],"into":[122],"several":[123],"domains;":[124],"report":[129],"results":[130],"obtained":[131],"control":[134],"problem":[135],"consisting":[136],"steering":[138],"boat":[140],"across":[141],"river.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}