{"id":"https://openalex.org/W2129120309","doi":null,"title":"Navigating through Temporal Difference","display_name":"Navigating through Temporal Difference","publication_year":1990,"publication_date":"1990-10-01","ids":{"openalex":"https://openalex.org/W2129120309","mag":"2129120309"},"language":"en","primary_location":{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:85048","doi":null,"is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/85048/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: Lippmann, R and Moody, JE and Touretzky, DS, (eds.) (pp. pp. 464-470). Morgan Kaufmann (1990)","raw_type":"Proceedings paper"},"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/A5075063030","display_name":"Peter Dayan","orcid":"https://orcid.org/0000-0003-3476-1839","observed_orcids":["https://orcid.org/0000-0003-3476-1839"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Peter Dayan","raw_affiliation_strings":["Centre for Cognitive Science & Department of Physics, University of Edinburgh, Edinburgh#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-3476-1839","affiliations":[{"raw_affiliation_string":"Centre for Cognitive Science & Department of Physics, University of Edinburgh, Edinburgh#TAB#","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075063030"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.4494,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.49978251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":93},"biblio":{"volume":"3","issue":null,"first_page":"464","last_page":"470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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":0.9955999851226807,"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/T10320","display_name":"Neural Networks and Applications","score":0.0015999999595806003,"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/T10448","display_name":"Memory and Neural Mechanisms","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.9829999804496765},{"id":"https://openalex.org/keywords/stimulus-encoding","display_name":"stimulus encoding","score":0.6470000147819519},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.9129999876022339},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7608877420425415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7391117811203003},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6154366135597229},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5849645137786865},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5471665859222412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5010056495666504},{"id":"https://openalex.org/C2779918689","wikidata":"https://www.wikidata.org/wiki/Q3771842","display_name":"Stimulus (psychology)","level":2,"score":0.4549703896045685},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3482779264450073},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32330143451690674},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.22802117466926575},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1287369430065155},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.12229439616203308},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07954204082489014},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07592025399208069},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:85048","doi":null,"is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/85048/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: Lippmann, R and Moody, JE and Touretzky, DS, (eds.) (pp. pp. 464-470). Morgan Kaufmann (1990)","raw_type":"Proceedings paper"},{"id":"pmh:oai:pure.mpg.de:item_3176206","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0005-1A48-E","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,"listed_in":[],"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":"Advances in Neural Information Processing Systems 3","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:2129120309","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/428-navigating-through-temporal-difference.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1610678877","https://openalex.org/W1993740947","https://openalex.org/W2100677568","https://openalex.org/W2103692957","https://openalex.org/W3011120880"],"related_works":["https://openalex.org/W7097838941","https://openalex.org/W7096888730","https://openalex.org/W7133223212","https://openalex.org/W7096371077","https://openalex.org/W6982400694","https://openalex.org/W903364491","https://openalex.org/W2582957638","https://openalex.org/W2056354534","https://openalex.org/W3037229067","https://openalex.org/W3147923547"],"abstract_inverted_index":{"Barto,":[0],"Sutton":[1],"and":[2,17,34],"Watkins":[3],"[2]":[4],"introduced":[5],"a":[6,10,41],"grid":[7],"task":[8],"as":[9],"didactic":[11],"example":[12],"of":[13,26,30,40,44],"temporal":[14],"difference":[15],"planning":[16],"asynchronous":[18],"dynamical":[19],"programming.":[20],"This":[21],"paper":[22],"considers":[23],"the":[24,28,31,37],"effects":[25],"changing":[27],"coding":[29],"input":[32],"stimulus,":[33],"demonstrates":[35],"that":[36],"self-supervised":[38],"learning":[39],"particular":[42],"form":[43],"hidden":[45],"unit":[46],"representation":[47],"improves":[48],"performance.":[49]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}