{"id":"https://openalex.org/W2034960258","doi":"https://doi.org/10.1109/devlrn.2012.6400860","title":"Scaling life-long off-policy learning","display_name":"Scaling life-long off-policy learning","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2034960258","doi":"https://doi.org/10.1109/devlrn.2012.6400860","mag":"2034960258"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2012.6400860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2012.6400860","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 Development and Learning and Epigenetic Robotics (ICDL)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1206.6262","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Department of Computing Science, University of Alberta, Canada","Reinforcement Learning and Artificial Intelligence Laboratory, Department of Computing Science, University of Alberta, Canada T6G 2E8"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, Department of Computing Science, University of Alberta, Canada T6G 2E8","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","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":["Department of Computing Science, University of Alberta, Canada","Reinforcement Learning and Artificial Intelligence Laboratory, Department of Computing Science, University of Alberta, Canada T6G 2E8"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, Department of Computing Science, University of Alberta, Canada T6G 2E8","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":["Department of Computing Science, University of Alberta, Canada","Reinforcement Learning and Artificial Intelligence Laboratory, Department of Computing Science, University of Alberta, Canada T6G 2E8"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, Department of Computing Science, University of Alberta, Canada T6G 2E8","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":0.0,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.13243859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"15","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9876999855041504,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7613723278045654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6503655910491943},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6435428261756897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6146824955940247},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4809824228286743},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.46894145011901855},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4431452453136444},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42190465331077576},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4146655201911926},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.41044679284095764},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15958210825920105},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1257549226284027},{"id":"https://openalex.org/keywords/economic-growth","display_name":"Economic growth","score":0.08237624168395996}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7613723278045654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503655910491943},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6435428261756897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6146824955940247},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4809824228286743},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.46894145011901855},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4431452453136444},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42190465331077576},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4146655201911926},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.41044679284095764},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15958210825920105},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1257549226284027},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.08237624168395996},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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":7,"locations":[{"id":"doi:10.1109/devlrn.2012.6400860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2012.6400860","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 Development and Learning and Epigenetic Robotics (ICDL)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1206.6262","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1206.6262","pdf_url":"https://arxiv.org/pdf/1206.6262","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.278.4819","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.278.4819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ualberta.ca/%7Esutton/papers/WMS-ICDL-2012.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.644.1258","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.644.1258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.swarthmore.edu/~meeden/DevelopmentalRobotics/horde2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.757.9220","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.757.9220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1206.6262.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.1206.6262","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1206.6262","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2034960258","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1206.6262","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1206.6262","pdf_url":"https://arxiv.org/pdf/1206.6262","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2034960258.pdf","grobid_xml":"https://content.openalex.org/works/W2034960258.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1540685400","https://openalex.org/W1562189966","https://openalex.org/W1646707810","https://openalex.org/W1979091739","https://openalex.org/W1991564165","https://openalex.org/W2012392077","https://openalex.org/W2075268401","https://openalex.org/W2101524054","https://openalex.org/W2109910161","https://openalex.org/W2121863487","https://openalex.org/W2132622533","https://openalex.org/W2138250415","https://openalex.org/W2139612737","https://openalex.org/W2146823374","https://openalex.org/W2158282517","https://openalex.org/W2164424353","https://openalex.org/W2208906386","https://openalex.org/W2276230513","https://openalex.org/W2293047233","https://openalex.org/W2336416123","https://openalex.org/W2570416447","https://openalex.org/W6607097208","https://openalex.org/W6632235069","https://openalex.org/W6679365036","https://openalex.org/W6683084483","https://openalex.org/W6688070083"],"related_works":["https://openalex.org/W3038131192","https://openalex.org/W3033478119","https://openalex.org/W2964345707","https://openalex.org/W2993208870","https://openalex.org/W1435107418","https://openalex.org/W2609002182","https://openalex.org/W3204728906","https://openalex.org/W3048681560","https://openalex.org/W3107370812","https://openalex.org/W3169100231","https://openalex.org/W2292003849","https://openalex.org/W1932176876","https://openalex.org/W2945104397","https://openalex.org/W3183420623","https://openalex.org/W60181528","https://openalex.org/W2144744117","https://openalex.org/W2801866268","https://openalex.org/W3008954574","https://openalex.org/W3152903268","https://openalex.org/W304768798"],"abstract_inverted_index":{"In":[0,17],"this":[1],"paper":[2],"we":[3,151],"pursue":[4],"an":[5],"approach":[6],"to":[7,36,60,94,98,175],"scaling":[8,50,67],"life-long":[9,18,44,99,180],"learning":[10,15,19,45,148,181],"using":[11,156],"parallel":[12,136],"off-policy":[13,73,96,115,147,159],"reinforcement":[14],"algorithms.":[16],"a":[20,25,47,84,102,118,169],"robot":[21],"continually":[22],"learns":[23],"from":[24,75],"life-time":[26],"of":[27,40,43,49,53,66,79,113,125,146],"experience,":[28],"slowly":[29],"acquiring":[30],"and":[31,34,137,178],"applying":[32],"skills":[33],"knowledge":[35],"new":[37,158],"situations.":[38],"Many":[39],"the":[41,51,58,76,106,111,142,157],"benefits":[42],"are":[46],"results":[48],"amount":[52],"training":[54],"data,":[55],"processed":[56],"by":[57,71,83],"robot,":[59,155],"long":[61],"sensorimotor":[62,80],"streams.":[63],"Another":[64],"dimension":[65],"can":[68,129,161],"be":[69,130],"added":[70],"allowing":[72],"sampling":[74],"unending":[77],"stream":[78],"data":[81],"generated":[82],"long-lived":[85],"robot.":[86,120],"Recent":[87],"algorithmic":[88],"developments":[89],"have":[90],"made":[91],"it":[92],"possible":[93],"apply":[95],"algorithms":[97,116],"learning,":[100],"in":[101,135,138,172],"sound":[103],"way,":[104],"for":[105],"first":[107,143],"time.":[108],"We":[109,121,140],"assess":[110],"scalability":[112],"these":[114],"on":[117],"physical":[119],"show":[122],"that":[123,153],"hundreds":[124],"accurate":[126],"multi-step":[127],"predictions":[128,164],"learned":[131],"about":[132,165],"several":[133],"policies":[134],"realtime.":[139],"present":[141],"online":[144],"measures":[145],"progress.":[149],"Finally":[150],"demonstrate":[152],"our":[154],"measures,":[160],"learn":[162],"8000":[163],"300":[166],"distinct":[167],"policies,":[168],"substantial":[170],"increase":[171],"scale":[173],"compared":[174],"previous":[176],"simulated":[177],"robotic":[179],"systems.":[182]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}