{"id":"https://openalex.org/W2100730540","doi":"https://doi.org/10.1109/cdc.2010.5717644","title":"Pathologies of temporal difference methods in approximate dynamic programming","display_name":"Pathologies of temporal difference methods in approximate dynamic programming","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2100730540","doi":"https://doi.org/10.1109/cdc.2010.5717644","mag":"2100730540"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2010.5717644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2010.5717644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/64641","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/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":["Department of Electrical Engineering and Computer Science, MIT, Cambridge, USA","Dept. of Electr. Engineering and Comp. Science, M.I.T., Cambridge, Mass., 02139, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, MIT, Cambridge, USA","institution_ids":[]},{"raw_affiliation_string":"Dept. of Electr. Engineering and Comp. Science, M.I.T., Cambridge, Mass., 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/I63966007"],"apc_list":null,"apc_paid":null,"fwci":2.7929,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91297647,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"32","issue":null,"first_page":"3034","last_page":"3039"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9932000041007996,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9811999797821045,"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/testbed","display_name":"Testbed","score":0.7160944938659668},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.7086276412010193},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6998469233512878},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6938198804855347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.652035653591156},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6150914430618286},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5860532522201538},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4695715606212616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43869760632514954},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4367637634277344},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4294254183769226},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41721513867378235},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.41685739159584045},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37147435545921326},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3237159550189972},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2847280502319336}],"concepts":[{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.7160944938659668},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.7086276412010193},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6998469233512878},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6938198804855347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652035653591156},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6150914430618286},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5860532522201538},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4695715606212616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43869760632514954},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4367637634277344},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4294254183769226},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41721513867378235},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.41685739159584045},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37147435545921326},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3237159550189972},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2847280502319336},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/cdc.2010.5717644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2010.5717644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.170.8978","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.170.8978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-mit.mit.edu/dimitrib/www/TD_Pathologies.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.6498","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.6498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.mit.edu/dimitrib/www/TD_Pathologies.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.186.510","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.186.510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mit.edu:8001/people/dimitrib/TD_Pathologies.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/64641","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/64641","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-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/64641","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/64641","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-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W145490631","https://openalex.org/W170657672","https://openalex.org/W565357261","https://openalex.org/W594357522","https://openalex.org/W1534175858","https://openalex.org/W1541084404","https://openalex.org/W1547105496","https://openalex.org/W1576452626","https://openalex.org/W1601081659","https://openalex.org/W2072931156","https://openalex.org/W2084202551","https://openalex.org/W2091565802","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2100857832","https://openalex.org/W2103626435","https://openalex.org/W2119567691","https://openalex.org/W2123859855","https://openalex.org/W2124477018","https://openalex.org/W2125510930","https://openalex.org/W2130801532","https://openalex.org/W2134932665","https://openalex.org/W2138178898","https://openalex.org/W2140778663","https://openalex.org/W2147839652","https://openalex.org/W2161608691","https://openalex.org/W2169982856","https://openalex.org/W2222696761","https://openalex.org/W2334782222","https://openalex.org/W2415292238","https://openalex.org/W2484957131","https://openalex.org/W2487144912","https://openalex.org/W2505159842","https://openalex.org/W2586680856","https://openalex.org/W2611866857","https://openalex.org/W2906165699","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3041202696","https://openalex.org/W3198350258","https://openalex.org/W4205326910","https://openalex.org/W4243772471","https://openalex.org/W4285719527","https://openalex.org/W4301630257","https://openalex.org/W6605909188","https://openalex.org/W6671393130","https://openalex.org/W6678558514","https://openalex.org/W6678900246","https://openalex.org/W6679257226"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W1914583973","https://openalex.org/W2130711276","https://openalex.org/W4308828368"],"abstract_inverted_index":{"Approximate":[0],"policy":[1,41],"iteration":[2,42],"methods":[3,59],"based":[4],"on":[5],"temporal":[6,125],"differences":[7],"are":[8],"popular":[9,98],"in":[10,70],"practice,":[11],"and":[12,29,124,141,163],"have":[13],"been":[14,66,83],"tested":[15],"extensively,":[16],"dating":[17],"to":[18,54,60,112],"the":[19,23,40,55,71,93,110,138,157],"early":[20],"nineties,":[21],"but":[22],"associated":[24],"convergence":[25],"behavior":[26],"is":[27,38,44],"complex,":[28],"not":[30,170],"well":[31],"understood":[32],"at":[33],"present.":[34],"An":[35],"important":[36],"question":[37],"whether":[39],"process":[43],"seriously":[45],"hampered":[46],"by":[47],"oscillations":[48],"between":[49],"poor":[50,61],"policies,":[51],"roughly":[52],"similar":[53],"attraction":[56],"of":[57,95,121,131,160],"gradient":[58],"local":[62],"minima.":[63],"There":[64],"has":[65,82,108],"little":[67],"apparent":[68],"concern":[69],"approximate":[72,101],"DP/reinforcement":[73],"learning":[74],"literature":[75],"about":[76],"this":[77,161],"possibility,":[78],"even":[79],"though":[80],"it":[81,168],"documented":[84],"with":[85,92],"several":[86],"simple":[87],"examples.":[88],"Recent":[89],"computational":[90],"experimentation":[91],"game":[94],"tetris,":[96],"a":[97,105,118,132,142],"testbed":[99],"for":[100],"DP":[102],"algorithms":[103],"over":[104],"15-year":[106],"period,":[107],"brought":[109],"issue":[111],"sharp":[113],"focus.":[114],"In":[115],"particular,":[116],"using":[117],"standard":[119],"set":[120],"22":[122],"features":[123,140],"difference":[126],"methods,":[127],"an":[128,146],"average":[129,149],"score":[130,150],"few":[133],"thousands":[134],"was":[135,151],"achieved.":[136],"Using":[137],"same":[139],"random":[143],"search":[144],"method,":[145],"overwhelmingly":[147],"better":[148],"achieved":[152],"(600,000-900,000).":[153],"The":[154],"paper":[155],"explains":[156],"likely":[158],"mechanism":[159],"phenomenon,":[162],"derives":[164],"conditions":[165],"under":[166],"which":[167],"will":[169],"occur.":[171]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"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":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}