{"id":"https://openalex.org/W2163065212","doi":"https://doi.org/10.1109/adprl.2009.4927519","title":"Efficient data reuse in value function approximation","display_name":"Efficient data reuse in value function approximation","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W2163065212","doi":"https://doi.org/10.1109/adprl.2009.4927519","mag":"2163065212"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2009.4927519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","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/A5073076975","display_name":"Hirotaka Hachiya","orcid":"https://orcid.org/0000-0003-3748-4101"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hirotaka Hachiya","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081780514","display_name":"Takayuki Akiyama","orcid":"https://orcid.org/0000-0002-3958-9452"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takayuki Akiyama","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072744508","display_name":"Masashi Sugiyama","orcid":"https://orcid.org/0000-0001-6658-6743"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Sugiyama","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I4210112925","display_name":"Max Planck Institute for Biological Cybernetics","ror":"https://ror.org/026nmvv73","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210112925"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Department Sch\u00f6lkopf, Max-Planck Institute of Biological Cybernetics, Tubingen, Germany"],"affiliations":[{"raw_affiliation_string":"Department Sch\u00f6lkopf, Max-Planck Institute of Biological Cybernetics, Tubingen, Germany","institution_ids":["https://openalex.org/I4210112925"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073076975"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28230473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"8","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10663","display_name":"Advanced Battery Technologies Research","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10663","display_name":"Advanced Battery Technologies Research","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10821","display_name":"Cardiovascular Function and Risk Factors","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9810000061988831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.8284730911254883},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.7298169732093811},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.693019688129425},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6496092081069946},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6394555568695068},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.6183738112449646},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5584744215011597},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5231436491012573},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5123435258865356},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.511372983455658},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.4237041473388672},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4011126458644867},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24691760540008545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2210063338279724},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19735518097877502},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1818864941596985},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.12546822428703308},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10398972034454346},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08625426888465881}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.8284730911254883},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.7298169732093811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.693019688129425},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6496092081069946},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6394555568695068},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.6183738112449646},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5584744215011597},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5231436491012573},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5123435258865356},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.511372983455658},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.4237041473388672},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4011126458644867},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24691760540008545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2210063338279724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19735518097877502},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1818864941596985},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.12546822428703308},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10398972034454346},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08625426888465881},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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":"doi:10.1109/adprl.2009.4927519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.165.8465","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.165.8465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.kyb.tuebingen.mpg.de/publications/attachments/ADPRL2009-Hachiya_%5B0%5D.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:461768","is_oa":false,"landing_page_url":"http://edoc.mpg.de/461768","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (IEEE ADPRL 2009), 8-15 (2009)","raw_type":"Conference-Paper"},{"id":"pmh:oai:pure.mpg.de:item_1789373","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0013-C4EB-A","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W189742998","https://openalex.org/W1514587017","https://openalex.org/W1576452626","https://openalex.org/W1600046456","https://openalex.org/W1880549478","https://openalex.org/W1969481231","https://openalex.org/W2034368206","https://openalex.org/W2068052921","https://openalex.org/W2109169869","https://openalex.org/W2109330238","https://openalex.org/W2121863487","https://openalex.org/W2125612430","https://openalex.org/W2130801532","https://openalex.org/W2133979692","https://openalex.org/W2165421048","https://openalex.org/W2253356247","https://openalex.org/W2403035479","https://openalex.org/W2796930440","https://openalex.org/W2950849043","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4229739412","https://openalex.org/W4242606736","https://openalex.org/W4285719527","https://openalex.org/W6607672814","https://openalex.org/W6630907848","https://openalex.org/W6634528131","https://openalex.org/W6635798015","https://openalex.org/W6639342821","https://openalex.org/W6676422638","https://openalex.org/W6679257226","https://openalex.org/W6684096483","https://openalex.org/W6691873557"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2387968248","https://openalex.org/W2120821724","https://openalex.org/W2350715914","https://openalex.org/W2101175215","https://openalex.org/W2379529020","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Off-policy":[0],"reinforcement":[1],"learning":[2],"is":[3,15,25,126],"aimed":[4],"at":[5],"efficiently":[6],"using":[7,85],"data":[8],"samples":[9],"gathered":[10],"from":[11,17],"a":[12,106,116],"policy":[13,47],"that":[14],"different":[16],"the":[18,34,42,45,49,60,63,97,111,123],"currently":[19],"optimized":[20],"policy.":[21,51],"A":[22],"common":[23],"approach":[24,125],"to":[26,75,94],"use":[27],"importance":[28,88],"sampling":[29,89],"techniques":[30],"for":[31,33,108],"compensating":[32],"bias":[35,100],"of":[36,62,118,122],"value":[37,64],"function":[38,65],"estimators":[39,66],"caused":[40],"by":[41],"difference":[43],"between":[44,99],"data-sampling":[46],"and":[48,70,101],"target":[50],"However,":[52],"existing":[53],"off-policy":[54],"methods":[55],"often":[56],"do":[57],"not":[58],"take":[59],"variance":[61],"explicitly":[67],"into":[68],"account":[69],"therefore":[71],"their":[72],"performance":[73],"tends":[74],"be":[76],"unstable.":[77],"To":[78],"cope":[79],"with":[80],"this":[81],"problem,":[82],"we":[83],"propose":[84],"an":[86],"adaptive":[87],"technique":[90],"which":[91],"allows":[92],"us":[93],"actively":[95],"control":[96],"trade-off":[98,112],"variance.":[102],"We":[103],"further":[104],"provide":[105],"method":[107],"optimally":[109],"determining":[110],"parameter":[113],"based":[114],"on":[115],"variant":[117],"cross-validation.":[119],"The":[120],"usefulness":[121],"proposed":[124],"demonstrated":[127],"through":[128],"simulated":[129],"swing-up":[130],"inverted-pendulum":[131],"problem.":[132]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}