{"id":"https://openalex.org/W2026641456","doi":"https://doi.org/10.1145/1102351.1102463","title":"TD(\u03bb) networks","display_name":"TD(\u03bb) networks","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2026641456","doi":"https://doi.org/10.1145/1102351.1102463","mag":"2026641456"},"language":"en","primary_location":{"id":"doi:10.1145/1102351.1102463","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on Machine learning - ICML '05","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075806019","display_name":"B. K. Tanner","orcid":"https://orcid.org/0000-0002-1474-177X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Brian Tanner","raw_affiliation_strings":["University of Alberta, Canada","University of Alberta,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"University of Alberta,Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004923102","display_name":"Richard S. Sutton","orcid":"https://orcid.org/0000-0002-3679-3415"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Richard S. Sutton","raw_affiliation_strings":["University of Alberta, Canada","University of Alberta,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"University of Alberta,Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":1.2323,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.79885081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"888","last_page":"895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9977999925613403,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9977999925613403,"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/T10028","display_name":"Topic Modeling","score":0.9898999929428101,"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/T11106","display_name":"Data Management and Algorithms","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.7629346251487732},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.662423312664032},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6430047154426575},{"id":"https://openalex.org/keywords/formalism","display_name":"Formalism (music)","score":0.5919750332832336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49440550804138184},{"id":"https://openalex.org/keywords/learning-network","display_name":"Learning network","score":0.48803654313087463},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39215201139450073},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38622820377349854},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3586704134941101},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.14597448706626892},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1389448344707489}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7629346251487732},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.662423312664032},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6430047154426575},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.5919750332832336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49440550804138184},{"id":"https://openalex.org/C2987015589","wikidata":"https://www.wikidata.org/wiki/Q1040098","display_name":"Learning network","level":2,"score":0.48803654313087463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39215201139450073},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38622820377349854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3586704134941101},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.14597448706626892},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1389448344707489},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1102351.1102463","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on Machine learning - ICML '05","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W70929694","https://openalex.org/W1540337045","https://openalex.org/W2029557545","https://openalex.org/W2042830238","https://openalex.org/W2100677568","https://openalex.org/W2132351269","https://openalex.org/W2158282517","https://openalex.org/W2169300227","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W4205958290","https://openalex.org/W4313313257","https://openalex.org/W2989932438"],"abstract_inverted_index":{"Temporal-difference":[0],"(TD)":[1],"networks":[2,33,94,119,145],"have":[3],"been":[4],"introduced":[5],"as":[6],"a":[7,17,68],"formalism":[8],"for":[9,31],"expressing":[10],"and":[11],"learning":[12,29,82],"grounded":[13],"world":[14],"knowledge":[15],"in":[16,98,109],"predictive":[18],"form":[19],"(Sutton":[20],"&":[21],"Tanner,":[22],"2005).":[23],"Like":[24],"conventional":[25,45],"TD(0)":[26],"methods,":[27],"the":[28,48,71,80,140],"algorithm":[30,50,136],"TD":[32,46,73,103,116,153],"uses":[34],"1-step":[35,72,127],"backups":[36,59],"to":[37,54],"train":[38],"prediction":[39],"units":[40],"about":[41],"future":[42,61],"events.":[43],"In":[44,63],"learning,":[47],"TD(\u03bb)":[49,81,85,93,118,144],"is":[51,77,146],"often":[52],"used":[53],"do":[55],"more":[56,99,149],"general":[57],"multi-step":[58],"of":[60,70,134,143,152],"predictions.":[62],"our":[64,135],"work,":[65],"we":[66,130],"introduce":[67],"generalization":[69],"network":[74],"specification":[75],"that":[76,91,108,111,137,139,151],"based":[78],"on":[79],"algorithm,":[83],"creating":[84],"networks.":[86,104,154],"We":[87,105],"present":[88,131],"experimental":[89],"results":[90],"show":[92,107],"can":[95,112],"learn":[96,121],"solutions":[97,122],"complex":[100],"environments":[101],"than":[102,125,150],"also":[106],"problems":[110],"be":[113],"solved":[114],"by":[115],"networks,":[117],"generally":[120],"much":[123],"faster":[124],"their":[126],"counterparts.":[128],"Finally,":[129],"an":[132],"analysis":[133],"shows":[138],"computational":[141],"cost":[142],"only":[147],"slightly":[148]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2016-06-24T00:00:00"}