{"id":"https://openalex.org/W2073549596","doi":"https://doi.org/10.1109/icsmc.2012.6378016","title":"Acquiring a broad range of empirical knowledge in real time by temporal-difference learning","display_name":"Acquiring a broad range of empirical knowledge in real time by temporal-difference learning","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W2073549596","doi":"https://doi.org/10.1109/icsmc.2012.6378016","mag":"2073549596"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2012.6378016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2012.6378016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/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":false,"raw_author_name":"Joseph Modayil","raw_affiliation_strings":["Reinforcement Learning and Artificial Intelligence Laboratory, Department of Computing Science, University of Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, Department of Computing Science, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101954122","display_name":"Adam White","orcid":"https://orcid.org/0000-0002-6449-0622"},"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, Department of Computing Science, University of Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, Department of Computing Science, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058237113","display_name":"Patrick M. Pilarski","orcid":"https://orcid.org/0000-0003-1686-2978"},"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":"Patrick M. Pilarski","raw_affiliation_strings":["Reinforcement Learning and Artificial Intelligence Laboratory, Department of Computing Science, University of Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, Department of Computing Science, 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, Department of Computing Science, University of Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, Department of Computing Science, 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":2.0813,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88174026,"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":"1903","last_page":"1910"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9868999719619751,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9853000044822693,"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/generality","display_name":"Generality","score":0.8790894746780396},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7608795762062073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7242250442504883},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.6452999711036682},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6349059343338013},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.6003265380859375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5183545351028442},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5024693012237549},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4788082242012024},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3994590640068054},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11614733934402466}],"concepts":[{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.8790894746780396},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7608795762062073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242250442504883},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.6452999711036682},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6349059343338013},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.6003265380859375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5183545351028442},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5024693012237549},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4788082242012024},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3994590640068054},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11614733934402466},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icsmc.2012.6378016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2012.6378016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.297.6135","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.297.6135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://webdocs.cs.ualberta.ca/~sutton/papers/MWPS-SMC-2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1424654272","https://openalex.org/W1689445748","https://openalex.org/W1979091739","https://openalex.org/W1991564165","https://openalex.org/W2100677568","https://openalex.org/W2109910161","https://openalex.org/W2117211893","https://openalex.org/W2121863487","https://openalex.org/W2126966171","https://openalex.org/W2132622533","https://openalex.org/W2134491302","https://openalex.org/W2138250415","https://openalex.org/W2139053308","https://openalex.org/W2153192722","https://openalex.org/W2172968643","https://openalex.org/W2208906386","https://openalex.org/W2473364827","https://openalex.org/W2570416447","https://openalex.org/W2611243847","https://openalex.org/W3041202696","https://openalex.org/W4214717370","https://openalex.org/W4235211477","https://openalex.org/W6679365036","https://openalex.org/W6680718018","https://openalex.org/W6683221847"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2122871747","https://openalex.org/W3114279067","https://openalex.org/W2724299411","https://openalex.org/W4365788246","https://openalex.org/W2913184176","https://openalex.org/W1936970628"],"abstract_inverted_index":{"Several":[0],"robot":[1,19,41,100],"capabilities":[2],"rely":[3],"on":[4],"predictions":[5,27,49,54,75,108,121],"about":[6,56,135],"the":[7,57,62,74,87,115,136,139,143],"temporally":[8,119],"extended":[9,120,153],"consequences":[10],"of":[11,47,59,61,80,89,133,138,159],"a":[12,18,32,39,77,96,99,130],"robot's":[13,63,140],"behaviour.":[14],"We":[15,85,145],"describe":[16],"how":[17,148],"can":[20,42,109,151],"both":[21],"learn":[22,43],"and":[23,44,65,82],"make":[24,45],"many":[25,66],"such":[26],"in":[28,123],"real":[29,124],"time":[30,125],"using":[31],"standard":[33],"algorithm.":[34],"Our":[35],"experiments":[36],"show":[37,147],"that":[38],"mobile":[40],"thousands":[46],"accurate":[48],"at":[50,70,103],"10":[51],"Hz.":[52,105],"The":[53,118],"are":[55],"future":[58],"all":[60],"sensors":[64],"internal":[67],"state":[68],"variables":[69],"multiple":[71],"time-scales.":[72],"All":[73],"share":[76],"single":[78],"set":[79],"features":[81],"learning":[83],"parameters.":[84],"demonstrate":[86],"generality":[88],"this":[90,127,149],"method":[91,128,150],"with":[92,142],"an":[93],"application":[94],"to":[95,112,154],"different":[97],"platform,":[98],"arm":[101],"operating":[102],"50":[104],"Here,":[106],"learned":[107,122],"be":[110,152],"used":[111],"measurably":[113],"improve":[114],"user":[116],"interface.":[117],"by":[126],"constitute":[129],"basic":[131],"form":[132],"knowledge":[134],"dynamics":[137],"interaction":[141],"environment.":[144],"also":[146],"express":[155],"more":[156],"general":[157],"forms":[158],"knowledge.":[160]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}