{"id":"https://openalex.org/W2170902787","doi":null,"title":"TD(0) converges provably faster than the residual gradient algorithm","display_name":"TD(0) converges provably faster than the residual gradient algorithm","publication_year":2003,"publication_date":"2003-08-21","ids":{"openalex":"https://openalex.org/W2170902787","mag":"2170902787"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.7028","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.7028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/conferences/icml2003/papers/105.pdf","raw_type":"text"},"volume":null,"type":"conference-paper","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/A5039367044","display_name":"Ralf Schoknecht","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schoknecht","raw_affiliation_strings":["Institute of Logic, Complexity and Deduction Systems, University of Karlsruhe, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Logic, Complexity and Deduction Systems, University of Karlsruhe, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010723602","display_name":"Artur Merke","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Artur Merke","raw_affiliation_strings":["Lehrstuhl Informatik 1, University of Dortmund, Dortmund, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehrstuhl Informatik 1, University of Dortmund, Dortmund, Germany#TAB#","institution_ids":["https://openalex.org/I200332995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5205,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.57153758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"680","last_page":"687"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.7699999809265137},{"id":"https://openalex.org/keywords/off-policy-learning","display_name":"off-policy learning","score":0.7409999966621399},{"id":"https://openalex.org/keywords/synchronous-learning","display_name":"synchronous learning","score":0.5},{"id":"https://openalex.org/keywords/linear-function-approximation","display_name":"linear function approximation","score":0.9120000004768372},{"id":"https://openalex.org/keywords/reinforcement-learning-algorithms","display_name":"reinforcement learning algorithms","score":0.6060000061988831}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.8119170665740967},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7180117964744568},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6894896030426025},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6815812587738037},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5498249530792236},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5268715023994446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4975893795490265},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.439268559217453},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4225849211215973},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4035799503326416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12915325164794922},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.7028","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.7028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/conferences/icml2003/papers/105.pdf","raw_type":"text"},{"id":"mag:2170902787","doi":null,"is_oa":false,"landing_page_url":"https://www.aaai.org/Papers/ICML/2003/ICML03-089.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W391578156","https://openalex.org/W1576452626","https://openalex.org/W1646707810","https://openalex.org/W2100677568","https://openalex.org/W2109330238","https://openalex.org/W2109910161","https://openalex.org/W2155143322","https://openalex.org/W3035235874"],"related_works":["https://openalex.org/W7097873004","https://openalex.org/W1969477885","https://openalex.org/W7008801889","https://openalex.org/W2473364827","https://openalex.org/W2776728688","https://openalex.org/W2155143322","https://openalex.org/W7130593181","https://openalex.org/W7097492100","https://openalex.org/W7133233823","https://openalex.org/W359568995"],"abstract_inverted_index":{"In":[0,21],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"there":[4],"has":[5],"been":[6],"some":[7],"experimental":[8],"evidence":[9],"that":[10,34,78],"the":[11,18,26,38,46,53,63,68,91,96],"residual":[12,49],"gradient":[13,50],"algorithm":[14,42,51],"converges":[15,43],"slower":[16],"than":[17,45],"TD(0)":[19,41],"algorithm.":[20],"this":[22],"paper,":[23],"we":[24],"use":[25],"concept":[27],"of":[28,71,93,95],"asymptotic":[29],"convergence":[30,69],"rate":[31],"to":[32],"prove":[33],"under":[35],"certain":[36],"conditions":[37],"synchronous":[39,47],"off-policy":[40],"faster":[44],"offpolicy":[48],"if":[52],"value":[54],"function":[55,83],"is":[56,62,85],"represented":[57],"in":[58],"tabular":[59],"form.":[60],"This":[61],"first":[64],"theoretical":[65],"result":[66],"comparing":[67],"behaviour":[70],"two":[72],"RL":[73],"algorithms.":[74],"We":[75],"also":[76],"show":[77],"as":[79,81],"soon":[80],"linear":[82],"approximation":[84],"involved":[86],"no":[87],"general":[88],"statement":[89],"concerning":[90],"superiority":[92],"one":[94],"algorithms":[97],"can":[98],"be":[99],"made.":[100],"1.":[101]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}