{"id":"https://openalex.org/W1991859114","doi":"https://doi.org/10.1109/adprl.2009.4927518","title":"A unified framework for temporal difference methods","display_name":"A unified framework for temporal difference methods","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W1991859114","doi":"https://doi.org/10.1109/adprl.2009.4927518","mag":"1991859114"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2009.4927518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927518","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":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/58831","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039911471","display_name":"Dimitri P. Bertsekas","orcid":"https://orcid.org/0000-0001-6909-7208"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dimitri P. Bertsekas","raw_affiliation_strings":["Laboratory of Information and Decision Systems (LIDS), Massachusetts Institute of Technology, MA, USA","Laboratory for Information and Decision Systems (LIDS), Massachusetts Institute of Technology, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory of Information and Decision Systems (LIDS), Massachusetts Institute of Technology, MA, USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory for Information and Decision Systems (LIDS), Massachusetts Institute of Technology, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5039911471"],"corresponding_institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.08142506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"13","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9947999715805054,"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":0.9947999715805054,"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":0.9853000044822693,"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/T10969","display_name":"Water resources management and optimization","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.7416167855262756},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6447829604148865},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5579624176025391},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.532894492149353},{"id":"https://openalex.org/keywords/connection","display_name":"Connection (principal bundle)","score":0.5262055993080139},{"id":"https://openalex.org/keywords/monotone-polygon","display_name":"Monotone polygon","score":0.5124145150184631},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5023369789123535},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.49202415347099304},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47578513622283936},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4581316113471985},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4568908214569092},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45599621534347534},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.44254475831985474},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42671138048171997},{"id":"https://openalex.org/keywords/projection-method","display_name":"Projection method","score":0.4210273027420044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3075842559337616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17489734292030334},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08855867385864258},{"id":"https://openalex.org/keywords/dykstras-projection-algorithm","display_name":"Dykstra's projection algorithm","score":0.081167072057724}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7416167855262756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6447829604148865},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5579624176025391},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.532894492149353},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.5262055993080139},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.5124145150184631},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5023369789123535},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.49202415347099304},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47578513622283936},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4581316113471985},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4568908214569092},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45599621534347534},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.44254475831985474},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42671138048171997},{"id":"https://openalex.org/C65557600","wikidata":"https://www.wikidata.org/wiki/Q7249451","display_name":"Projection method","level":3,"score":0.4210273027420044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3075842559337616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17489734292030334},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08855867385864258},{"id":"https://openalex.org/C202426404","wikidata":"https://www.wikidata.org/wiki/Q5318686","display_name":"Dykstra's projection algorithm","level":2,"score":0.081167072057724},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/adprl.2009.4927518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927518","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:dspace.mit.edu:1721.1/58831","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/58831","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE","raw_type":"http://purl.org/eprint/type/JournalArticle"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/58831","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/58831","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE","raw_type":"http://purl.org/eprint/type/JournalArticle"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1494807058","display_name":"Control over Networks","funder_award_id":"0801549","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1507222174","https://openalex.org/W1518539242","https://openalex.org/W1519983908","https://openalex.org/W1576452626","https://openalex.org/W1603765807","https://openalex.org/W2019172585","https://openalex.org/W2062541405","https://openalex.org/W2072931156","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2119567691","https://openalex.org/W2132351269","https://openalex.org/W2139418546","https://openalex.org/W2156737235","https://openalex.org/W2158278868","https://openalex.org/W2165418472","https://openalex.org/W2334782222","https://openalex.org/W2415292238","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3041202696","https://openalex.org/W4301630257","https://openalex.org/W4301791716","https://openalex.org/W6683392610"],"related_works":["https://openalex.org/W1980381208","https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2364594919","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W2389185103"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,6,20,26,31,62],"unified":[3],"framework":[4,58],"for":[5,67],"broad":[7],"class":[8],"of":[9,19,34,75,96],"methods":[10,40,66,82],"to":[11,90],"solve":[12],"projected":[13],"equations":[14],"that":[15],"approximate":[16,43],"the":[17,76,97],"solution":[18],"high-dimensional":[21],"fixed":[22],"point":[23],"problem":[24],"within":[25],"subspace":[27,77],"S":[28,78],"spanned":[29],"by":[30],"small":[32],"number":[33],"basis":[35],"functions":[36],"or":[37],"features.":[38],"These":[39],"originated":[41],"in":[42],"dynamic":[44],"programming":[45],"(DP),":[46],"where":[47],"they":[48],"are":[49],"collectively":[50],"known":[51],"as":[52],"temporal":[53],"difference":[54],"(TD)":[55],"methods.":[56],"Our":[57,81],"is":[59],"based":[60],"on":[61],"connection":[63],"with":[64],"projection":[65],"monotone":[68],"variational":[69],"inequalities,":[70],"which":[71,101],"involve":[72],"alternative":[73],"representations":[74],"(feature":[79],"scaling).":[80],"admit":[83],"simulation-based":[84],"implementations,":[85],"and":[86,107],"even":[87],"when":[88],"specialized":[89],"DP":[91],"problems,":[92],"include":[93],"extensions/new":[94],"versions":[95],"standard":[98],"TD":[99],"algorithms,":[100],"offer":[102],"some":[103],"special":[104],"implementation":[105],"advantages":[106],"reduced":[108],"overhead.":[109]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}