{"id":"https://openalex.org/W2159752377","doi":"https://doi.org/10.1177/1059712313511648","title":"Multi-timescale nexting in a reinforcement learning robot","display_name":"Multi-timescale nexting in a reinforcement learning robot","publication_year":2014,"publication_date":"2014-02-07","ids":{"openalex":"https://openalex.org/W2159752377","doi":"https://doi.org/10.1177/1059712313511648","mag":"2159752377"},"language":"en","primary_location":{"id":"doi:10.1177/1059712313511648","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1059712313511648","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-article"},"type":"article","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/A5054065284","display_name":"Joseph Modayil","orcid":null},"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":true,"raw_author_name":"Joseph Modayil","raw_affiliation_strings":["Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103825231","display_name":"Adam White","orcid":null},"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":"Adam White","raw_affiliation_strings":["Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, 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":["Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054065284"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":4.4202,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.95111819,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"22","issue":"2","first_page":"146","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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/T11883","display_name":"Embodied and Extended Cognition","score":0.9846000075340271,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7562499642372131},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7078211903572083},{"id":"https://openalex.org/keywords/laptop","display_name":"Laptop","score":0.6690694689750671},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.61935955286026},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.610088050365448},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5493648648262024},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5442940592765808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5345410704612732},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4812178909778595},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44800055027008057},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.44561105966567993},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4125063419342041},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3770585060119629},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1705496609210968},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.11315160989761353}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7562499642372131},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7078211903572083},{"id":"https://openalex.org/C2780008327","wikidata":"https://www.wikidata.org/wiki/Q3962","display_name":"Laptop","level":2,"score":0.6690694689750671},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.61935955286026},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.610088050365448},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5493648648262024},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5442940592765808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5345410704612732},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4812178909778595},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44800055027008057},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.44561105966567993},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4125063419342041},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3770585060119629},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1705496609210968},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.11315160989761353},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1059712313511648","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1059712313511648","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319907","display_name":"Alberta Innovates - Technology Futures","ror":"https://ror.org/00ynafe15"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W16046748","https://openalex.org/W178169250","https://openalex.org/W193299737","https://openalex.org/W292508636","https://openalex.org/W354832773","https://openalex.org/W359568995","https://openalex.org/W656758117","https://openalex.org/W774034202","https://openalex.org/W1424654272","https://openalex.org/W1490191165","https://openalex.org/W1491843047","https://openalex.org/W1515851193","https://openalex.org/W1537398163","https://openalex.org/W1540337045","https://openalex.org/W1558731210","https://openalex.org/W1577238357","https://openalex.org/W1592402337","https://openalex.org/W1594201624","https://openalex.org/W1594216983","https://openalex.org/W1655784964","https://openalex.org/W1965324089","https://openalex.org/W1977124459","https://openalex.org/W2011386395","https://openalex.org/W2013896409","https://openalex.org/W2024390895","https://openalex.org/W2024760831","https://openalex.org/W2027648864","https://openalex.org/W2028418738","https://openalex.org/W2032139276","https://openalex.org/W2036374621","https://openalex.org/W2039263255","https://openalex.org/W2075268401","https://openalex.org/W2084807600","https://openalex.org/W2088234494","https://openalex.org/W2100677568","https://openalex.org/W2101524054","https://openalex.org/W2109008048","https://openalex.org/W2109910161","https://openalex.org/W2112441941","https://openalex.org/W2115271248","https://openalex.org/W2121863487","https://openalex.org/W2123786976","https://openalex.org/W2132622533","https://openalex.org/W2145938889","https://openalex.org/W2151742051","https://openalex.org/W2153791616","https://openalex.org/W2154844948","https://openalex.org/W2158282517","https://openalex.org/W2160371091","https://openalex.org/W2165905123","https://openalex.org/W2169269081","https://openalex.org/W2169300227","https://openalex.org/W2172968643","https://openalex.org/W2312491913","https://openalex.org/W2341514930","https://openalex.org/W2473364827","https://openalex.org/W2539402368","https://openalex.org/W2569188995","https://openalex.org/W2570416447","https://openalex.org/W2595697910","https://openalex.org/W2597289420","https://openalex.org/W2598912124","https://openalex.org/W2602753196","https://openalex.org/W2611243847","https://openalex.org/W2798058877","https://openalex.org/W2918565994","https://openalex.org/W2963940912","https://openalex.org/W2999905431","https://openalex.org/W3021292343","https://openalex.org/W3041202696","https://openalex.org/W3102923851","https://openalex.org/W3150997492","https://openalex.org/W4205773779","https://openalex.org/W4214717370","https://openalex.org/W4231367092","https://openalex.org/W4231832368","https://openalex.org/W4238215782","https://openalex.org/W4254764272","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2386410636","https://openalex.org/W2341346307","https://openalex.org/W2025663273","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W3099153698","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W3038962357"],"abstract_inverted_index":{"The":[0,33],"term":[1],"\u2018nexting\u2019":[2],"has":[3],"been":[4],"used":[5,91,106,168],"by":[6,212],"psychologists":[7],"to":[8,10,19,35,59,76,166,179,193,251],"refer":[9],"the":[11,87,101,112,116,134,151,173,214,221,256],"propensity":[12],"of":[13,41,45,66,86,100,129,133,203,220,228,255,258],"people":[14],"and":[15,30,43,111,139,175,223],"many":[16,196],"other":[17],"animals":[18],"continually":[20],"predict":[21,195],"what":[22],"will":[23],"happen":[24],"next":[25,60],"in":[26,61,92],"an":[27,97],"immediate,":[28],"local,":[29],"personal":[31],"sense.":[32],"ability":[34],"\u2018next\u2019":[36],"constitutes":[37],"a":[38,55,84,108,127,147,187,200,218,243,249],"basic":[39],"kind":[40],"awareness":[42],"knowledge":[44,254],"one\u2019s":[46],"environment.":[47,260],"In":[48],"this":[49,229],"paper":[50],"we":[51],"present":[52],"results":[53],"with":[54,156,237],"robot":[56,174,250],"that":[57,120,225],"learns":[58],"real":[62],"time,":[63],"making":[64],"thousands":[65],"predictions":[67,80,227],"about":[68],"sensory":[69,102],"input":[70,103],"signals":[71,104,198],"at":[72],"timescales":[73,211],"from":[74],"0.1":[75],"8":[77],"seconds.":[78],"Our":[79],"are":[81],"formulated":[82],"as":[83,107,126],"generalization":[85],"value":[88],"functions":[89],"commonly":[90],"reinforcement":[93],"learning,":[94],"where":[95],"now":[96],"arbitrary":[98],"function":[99,128,158,219],"is":[105,162],"pseudo":[109],"reward,":[110],"discount":[113,215],"rate":[114,216],"determines":[115],"timescale.":[117],"We":[118,205],"show":[119,224],"six":[121,130],"thousand":[122,131],"predictions,":[123],"each":[124],"computed":[125],"features":[132],"state,":[135],"can":[136,233],"be":[137,167,217,235],"learned":[138,236],"updated":[140],"online":[141],"ten":[142],"times":[143],"per":[144],"second":[145],"on":[146,172],"laptop":[148],"computer,":[149],"using":[150],"standard":[152],"temporal-difference(":[153],"\u03bb)":[154],"algorithm":[155],"linear":[157],"approximation.":[159],"This":[160],"approach":[161],"sufficiently":[163,176],"computationally":[164],"efficient":[165,178],"for":[169,248],"real-time":[170],"learning":[171],"data":[177],"achieve":[180],"substantial":[181,238],"accuracy":[182],"within":[183],"30":[184],"minutes.":[185],"Moreover,":[186],"single":[188],"tile-coded":[189],"feature":[190],"representation":[191],"suffices":[192],"accurately":[194],"different":[197],"over":[199],"significant":[201],"range":[202],"timescales.":[204],"also":[206,234],"extend":[207],"nexting":[208,226,241],"beyond":[209],"simple":[210,244],"letting":[213],"state":[222],"more":[230],"general":[231],"form":[232],"accuracy.":[239],"General":[240],"provides":[242],"yet":[245],"powerful":[246],"mechanism":[247],"acquire":[252],"predictive":[253],"dynamics":[257],"its":[259]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}