{"id":"https://openalex.org/W2607014226","doi":"https://doi.org/10.1109/tnnls.2017.2690910","title":"Learning to Predict Consequences as a Method of Knowledge Transfer in Reinforcement Learning","display_name":"Learning to Predict Consequences as a Method of Knowledge Transfer in Reinforcement Learning","publication_year":2017,"publication_date":"2017-04-17","ids":{"openalex":"https://openalex.org/W2607014226","doi":"https://doi.org/10.1109/tnnls.2017.2690910","mag":"2607014226","pmid":"https://pubmed.ncbi.nlm.nih.gov/28436902"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2017.2690910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2017.2690910","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5087985487","display_name":"Eric Chalmers","orcid":"https://orcid.org/0000-0003-2985-1397"},"institutions":[{"id":"https://openalex.org/I107949126","display_name":"University of Lethbridge","ror":"https://ror.org/044j76961","country_code":"CA","type":"education","lineage":["https://openalex.org/I107949126"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Eric Chalmers","raw_affiliation_strings":["Department of Neuroscience, the University of Lethbridge, Lethbridge, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0003-2985-1397","affiliations":[{"raw_affiliation_string":"Department of Neuroscience, the University of Lethbridge, Lethbridge, AB, Canada","institution_ids":["https://openalex.org/I107949126"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067181021","display_name":"Edgar Bermudez-Contreras","orcid":"https://orcid.org/0000-0002-4937-1780"},"institutions":[{"id":"https://openalex.org/I107949126","display_name":"University of Lethbridge","ror":"https://ror.org/044j76961","country_code":"CA","type":"education","lineage":["https://openalex.org/I107949126"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Edgar Bermudez Contreras","raw_affiliation_strings":["Department of Neuroscience, the University of Lethbridge, Lethbridge, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neuroscience, the University of Lethbridge, Lethbridge, AB, Canada","institution_ids":["https://openalex.org/I107949126"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055297169","display_name":"Brandon Robertson","orcid":null},"institutions":[{"id":"https://openalex.org/I107949126","display_name":"University of Lethbridge","ror":"https://ror.org/044j76961","country_code":"CA","type":"education","lineage":["https://openalex.org/I107949126"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Brandon Robertson","raw_affiliation_strings":["Department of Neuroscience, the University of Lethbridge, Lethbridge, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neuroscience, the University of Lethbridge, Lethbridge, AB, Canada","institution_ids":["https://openalex.org/I107949126"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047020510","display_name":"Artur Luczak","orcid":"https://orcid.org/0000-0002-4929-5781"},"institutions":[{"id":"https://openalex.org/I107949126","display_name":"University of Lethbridge","ror":"https://ror.org/044j76961","country_code":"CA","type":"education","lineage":["https://openalex.org/I107949126"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Artur Luczak","raw_affiliation_strings":["Department of Neuroscience, the University of Lethbridge, Lethbridge, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neuroscience, the University of Lethbridge, Lethbridge, AB, Canada","institution_ids":["https://openalex.org/I107949126"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044129448","display_name":"Aaron J. Gruber","orcid":"https://orcid.org/0000-0003-2700-5429"},"institutions":[{"id":"https://openalex.org/I107949126","display_name":"University of Lethbridge","ror":"https://ror.org/044j76961","country_code":"CA","type":"education","lineage":["https://openalex.org/I107949126"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Aaron Gruber","raw_affiliation_strings":["Department of Neuroscience, the University of Lethbridge, Lethbridge, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neuroscience, the University of Lethbridge, Lethbridge, AB, Canada","institution_ids":["https://openalex.org/I107949126"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8913,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.92797704,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"29","issue":"6","first_page":"2259","last_page":"2270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9825999736785889,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8166329860687256},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7625789642333984},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.6183839440345764},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5322852730751038},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.49944162368774414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47727125883102417},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4754216969013214},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.472445547580719},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.4504682123661041},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.44214481115341187},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4149324297904968},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.2176510989665985},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.21025466918945312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166329860687256},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7625789642333984},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.6183839440345764},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5322852730751038},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49944162368774414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47727125883102417},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4754216969013214},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.472445547580719},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.4504682123661041},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.44214481115341187},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4149324297904968},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2176510989665985},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.21025466918945312},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014163","descriptor_name":"Transfer, Psychology","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D014163","descriptor_name":"Transfer, Psychology","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D014163","descriptor_name":"Transfer, Psychology","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019359","descriptor_name":"Knowledge","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019359","descriptor_name":"Knowledge","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019359","descriptor_name":"Knowledge","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D065854","descriptor_name":"Spatial Navigation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D065854","descriptor_name":"Spatial Navigation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D065854","descriptor_name":"Spatial Navigation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2017.2690910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2017.2690910","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:28436902","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28436902","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G672323635","display_name":null,"funder_award_id":"331011712","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W99485931","https://openalex.org/W309749295","https://openalex.org/W1488730473","https://openalex.org/W1491843047","https://openalex.org/W1492014007","https://openalex.org/W1497825134","https://openalex.org/W1503421559","https://openalex.org/W1544598807","https://openalex.org/W1554015367","https://openalex.org/W1563109146","https://openalex.org/W1977124459","https://openalex.org/W1977655452","https://openalex.org/W1981110271","https://openalex.org/W1985161922","https://openalex.org/W1986014385","https://openalex.org/W1990654808","https://openalex.org/W1993277309","https://openalex.org/W2000784441","https://openalex.org/W2007584825","https://openalex.org/W2012204020","https://openalex.org/W2015858749","https://openalex.org/W2018480107","https://openalex.org/W2020573190","https://openalex.org/W2024637532","https://openalex.org/W2026724928","https://openalex.org/W2048226872","https://openalex.org/W2050688638","https://openalex.org/W2051850587","https://openalex.org/W2055921164","https://openalex.org/W2070678636","https://openalex.org/W2082689007","https://openalex.org/W2088862785","https://openalex.org/W2091118421","https://openalex.org/W2097381042","https://openalex.org/W2097498341","https://openalex.org/W2103263764","https://openalex.org/W2105546430","https://openalex.org/W2106953752","https://openalex.org/W2116064496","https://openalex.org/W2118656144","https://openalex.org/W2120079537","https://openalex.org/W2121863487","https://openalex.org/W2132622533","https://openalex.org/W2134807560","https://openalex.org/W2137004246","https://openalex.org/W2139465937","https://openalex.org/W2146881125","https://openalex.org/W2159752377","https://openalex.org/W2161966552","https://openalex.org/W2162206751","https://openalex.org/W2170164558","https://openalex.org/W2172158418","https://openalex.org/W2488247662","https://openalex.org/W2489939061","https://openalex.org/W2515676083","https://openalex.org/W2517639096","https://openalex.org/W2519881245","https://openalex.org/W2554885577","https://openalex.org/W2561161270","https://openalex.org/W2573488511","https://openalex.org/W2578066652","https://openalex.org/W2903489506","https://openalex.org/W3103379718","https://openalex.org/W4214717370","https://openalex.org/W4245108548","https://openalex.org/W4254764272","https://openalex.org/W4285719527","https://openalex.org/W6629152578","https://openalex.org/W6629461247","https://openalex.org/W6633172667","https://openalex.org/W6674600207","https://openalex.org/W6674664616","https://openalex.org/W6676297359","https://openalex.org/W6679365036","https://openalex.org/W6679908558","https://openalex.org/W6683545760","https://openalex.org/W6683603353","https://openalex.org/W6726468317","https://openalex.org/W6732224557"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"The":[0,41],"reinforcement":[1],"learning":[2,168,193],"(RL)":[3],"paradigm":[4],"allows":[5],"agents":[6,21],"to":[7,25,32,43,62,80,136,166],"solve":[8,81],"tasks":[9,34],"through":[10],"trial-and-error":[11],"learning.":[12],"To":[13],"be":[14,23],"capable":[15],"of":[16,65,111,128],"efficient,":[17],"long-term":[18],"learning,":[19],"RL":[20,58],"should":[22],"able":[24],"apply":[26],"knowledge":[27,50,129,163,184],"gained":[28],"in":[29,38,93,131,155],"the":[30,39,82,100,133,150],"past":[31],"new":[33],"they":[35],"may":[36,47,98,107],"encounter":[37],"future.":[40],"ability":[42],"predict":[44,137],"actions'":[45,138],"consequences":[46,140],"facilitate":[48],"such":[49],"transfer.":[51],"We":[52,115],"consider":[53],"here":[54],"domains":[55],"where":[56],"an":[57,121],"agent":[59,134],"has":[60],"access":[61],"two":[63],"kinds":[64],"information:":[66],"agent-centric":[67,105,142,165],"information":[68,97,106,148],"with":[69,85],"constant":[70],"semantics":[71,86],"across":[72],"tasks,":[73],"and":[74,152,159,177,190],"environment-centric":[75,96,167],"information,":[76],"which":[77,132],"is":[78],"necessary":[79],"task,":[83],"but":[84],"that":[87,117,182],"differ":[88],"between":[89],"tasks.":[90],"For":[91],"example,":[92],"robot":[94],"navigation,":[95],"include":[99,108],"robot's":[101],"geographic":[102],"location,":[103],"while":[104],"sensor":[109],"readings":[110],"various":[112],"nearby":[113],"obstacles.":[114],"propose":[116],"these":[118],"situations":[119],"provide":[120],"opportunity":[122],"for":[123],"a":[124,156],"very":[125],"natural":[126],"style":[127],"transfer,":[130],"learns":[135],"environmental":[139],"using":[141],"information.":[143],"These":[144],"predictions":[145],"contain":[146],"important":[147],"about":[149],"affordances":[151],"dangers":[153],"present":[154],"novel":[157],"environment,":[158],"can":[160,187],"effectively":[161],"transfer":[162,185],"from":[164],"systems.":[169],"Using":[170],"several":[171],"example":[172],"problems":[173],"including":[174],"spatial":[175],"navigation":[176],"network":[178],"routing,":[179],"we":[180],"show":[181],"our":[183],"approach":[186],"allow":[188],"faster":[189],"lower":[191],"cost":[192],"than":[194],"existing":[195],"alternatives.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-17T08:01:34.144755","created_date":"2025-10-10T00:00:00"}