{"id":"https://openalex.org/W2093652578","doi":"https://doi.org/10.1109/adprl.2011.5967368","title":"Fitted policy search","display_name":"Fitted policy search","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2093652578","doi":"https://doi.org/10.1109/adprl.2011.5967368","mag":"2093652578"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2011.5967368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},"type":"article","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/A5108708631","display_name":"Martino Migliavacca","orcid":null},"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":true,"raw_author_name":"Martino Migliavacca","raw_affiliation_strings":["Department of Electronics and Information, Politecnico di Milano, Milan, Italy","Department of Electronics and Information, Politecnico di Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Department 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, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059473672","display_name":"Alessio Pecorino","orcid":null},"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":"Alessio Pecorino","raw_affiliation_strings":["Department of Electronics and Information, Politecnico di Milano, Milan, Italy","Department of Electronics and Information, Politecnico di Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Department 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, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091526684","display_name":"Matteo Pirotta","orcid":null},"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":"Matteo Pirotta","raw_affiliation_strings":["Department of Electronics and Information, Politecnico di Milano, Milan, Italy","Department of Electronics and Information, Politecnico di Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Department 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, 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"},"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","Department of Electronics and Information, Politecnico di Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Department 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, 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"},"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","Department of Electronics and Information, Politecnico di Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Department 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, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5108708631"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":0.4276,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72850901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"12","issue":null,"first_page":"287","last_page":"294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9925000071525574,"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":0.9882000088691711,"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":0.7904224395751953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7475380301475525},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.581935703754425},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5752872228622437},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5638926029205322},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5299671292304993},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5182540416717529},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.5102097988128662},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5066066980361938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5018777847290039},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.49633556604385376},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46177470684051514},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4148886799812317},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16481685638427734},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14617064595222473},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.08717629313468933}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7904224395751953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7475380301475525},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.581935703754425},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5752872228622437},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5638926029205322},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5299671292304993},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5182540416717529},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.5102097988128662},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5066066980361938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5018777847290039},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.49633556604385376},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46177470684051514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4148886799812317},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16481685638427734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14617064595222473},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.08717629313468933},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/adprl.2011.5967368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/608650","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/608650","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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W186489565","https://openalex.org/W1497256448","https://openalex.org/W1502364872","https://openalex.org/W1503196123","https://openalex.org/W1506832649","https://openalex.org/W1533424938","https://openalex.org/W1550698229","https://openalex.org/W1594783240","https://openalex.org/W1601974704","https://openalex.org/W1646707810","https://openalex.org/W1659842140","https://openalex.org/W2056132907","https://openalex.org/W2101533993","https://openalex.org/W2103464184","https://openalex.org/W2114537044","https://openalex.org/W2117355432","https://openalex.org/W2120346334","https://openalex.org/W2125612430","https://openalex.org/W2126685977","https://openalex.org/W2127107099","https://openalex.org/W2135826251","https://openalex.org/W2139053308","https://openalex.org/W2139418546","https://openalex.org/W2144357723","https://openalex.org/W2146737184","https://openalex.org/W2155027007","https://openalex.org/W2158462832","https://openalex.org/W2233997862","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W4245296547","https://openalex.org/W6606719070","https://openalex.org/W6607515316","https://openalex.org/W6629610141","https://openalex.org/W6630376126","https://openalex.org/W6631829558","https://openalex.org/W6635508374","https://openalex.org/W6635991215","https://openalex.org/W6675078014","https://openalex.org/W6677049199","https://openalex.org/W6677549092","https://openalex.org/W6677737365","https://openalex.org/W6678925830","https://openalex.org/W6681206011","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W2051058708","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312"],"abstract_inverted_index":{"In":[0,59,166],"this":[1,167],"paper":[2],"we":[3,127],"address":[4],"the":[5,19,45,69,83,100,107,129,137,145,154,158,162,174,205,209,212],"combination":[6],"of":[7,21,77,109,140,176,211],"batch":[8],"reinforcement-learning":[9],"(BRL)":[10],"techniques":[11],"with":[12,51],"direct":[13],"policy":[14,89,131,142],"search":[15,132],"(DPS)":[16],"algorithms":[17,26],"in":[18,38,48,113,135,161],"context":[20],"robot":[22],"learning.":[23],"Batch":[24],"value-based":[25],"(such":[27],"as":[28,56],"fitted":[29,130],"Q-iteration)":[30],"have":[31],"been":[32],"proved":[33],"to":[34,74,105,153,172,188,203],"outperform":[35],"online":[36],"ones":[37],"many":[39,114],"complex":[40],"applications,":[41],"but":[42],"they":[43],"share":[44],"same":[46],"difficulties":[47],"solving":[49],"problems":[50],"continuous":[52],"action":[53],"spaces,":[54],"such":[55,125],"robotic":[57,116,190,199],"ones.":[58],"these":[60,86],"cases,":[61],"actor-critic":[62],"and":[63,91,179,207],"DPS":[64,180],"methods":[65,87],"are":[66,94],"preferable,":[67],"since":[68,98],"optimization":[70,146],"process":[71,147],"is":[72,118,148,170,201],"limited":[73],"a":[75,196],"family":[76],"parameterized":[78],"(usually":[79],"smooth)":[80],"policies.":[81],"On":[82],"other":[84],"hand,":[85],"(e.g.,":[88],"gradient":[90],"evolutionary":[92],"methods)":[93],"generally":[95],"very":[96],"expensive,":[97],"finding":[99],"optimal":[101],"parameterization":[102],"may":[103],"require":[104],"evaluate":[106,208],"performance":[108],"several":[110],"policies,":[111],"which":[112,136],"real":[115,197],"applications":[117],"unfeasible":[119],"or":[120],"even":[121],"dangerous.":[122],"To":[123],"overcome":[124],"problems,":[126],"exploit":[128],"(FPS)":[133],"approach,":[134],"expected":[138],"return":[139],"any":[141],"considered":[143],"during":[144],"evaluated":[149],"offline":[150],"(without":[151],"resorting":[152],"robot)":[155],"by":[156],"reusing":[157],"data":[159],"collected":[160],"initial":[163],"exploration":[164],"phase.":[165],"way,":[168],"it":[169],"possible":[171],"take":[173],"advantages":[175],"both":[177],"BRL":[178],"algorithms,":[181],"thus":[182],"achieving":[183],"an":[184],"effective":[185],"learning":[186],"approach":[187],"solve":[189],"problems.":[191],"A":[192],"balancing":[193],"task":[194],"on":[195],"two-wheeled":[198],"pendulum":[200],"used":[202],"analyze":[204],"properties":[206],"effectiveness":[210],"FPS":[213],"approach.":[214]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}