{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:52:08Z","timestamp":1781621528214,"version":"3.54.5"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2018,6,1]],"date-time":"2018-06-01T00:00:00Z","timestamp":1527811200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["331011712"],"award-info":[{"award-number":["331011712"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1109\/tnnls.2017.2690910","type":"journal-article","created":{"date-parts":[[2017,4,17]],"date-time":"2017-04-17T18:10:13Z","timestamp":1492452613000},"page":"2259-2270","source":"Crossref","is-referenced-by-count":46,"title":["Learning to Predict Consequences as a Method of Knowledge Transfer in Reinforcement Learning"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2985-1397","authenticated-orcid":false,"given":"Eric","family":"Chalmers","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edgar Bermudez","family":"Contreras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brandon","family":"Robertson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Artur","family":"Luczak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron","family":"Gruber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"30","article-title":"Context transfer and Q-transferable tasks","author":"mousavi","year":"2015","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/428567"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2014.09.009"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/1059712316664570"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980200"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ChiCC.2015.7260106"},{"key":"ref36","first-page":"672","article-title":"General game learning using knowledge transfer","author":"banerjee","year":"2007","journal-title":"Proc IJCAI"},{"key":"ref35","first-page":"1333","article-title":"Transfer in reinforcement learning via shared features","volume":"13","author":"konidaris","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref34","author":"wiewiora","year":"2011","journal-title":"Potential-based shaping and Q-value initialization are equivalent"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5225-4"},{"key":"ref62","first-page":"1955","article-title":"Provably efficient learning with typed parametric models","volume":"10","author":"brunskill","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref61","first-page":"1417","article-title":"Online linear regression and its application to model-based reinforcement learning","author":"strehl","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-012-9200-2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2007.08.001"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2007.01.004"},{"key":"ref27","first-page":"142331216649655","article-title":"Transferring knowledge from human-demonstration trajectories to reinforcement learning","author":"wang","year":"2016","journal-title":"Trans Inst Meas Control"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2441511"},{"key":"ref29","article-title":"Reinforcement learning in sensor-guided aibo robots","author":"birdwell","year":"2007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/h0074898"},{"key":"ref1","author":"straddon","year":"1983","journal-title":"Adaptive Behavior and Learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.2009.5423227"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.006"},{"key":"ref21","first-page":"27","article-title":"Continuous-state reinforcement learning with fuzzy approximation","author":"bu?oniu","year":"2008","journal-title":"Adaptive Agents and Multi-Agent Systems III Adaptation and Multi-Agent Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-013-9242-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/11494669_52"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.2007.382878"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref50","first-page":"740","article-title":"Efficient reinforcement learning in factored MDPs","volume":"16","author":"kearns","year":"1999","journal-title":"Proc IJCAI"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-013-9406-y"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1137\/0110037"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref56","first-page":"761","article-title":"Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction","volume":"2","author":"sutton","year":"2011","journal-title":"10th Int Conf Auton Agents Multiagent Syst"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"ref54","first-page":"213","article-title":"R-max-a general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref53","author":"koenig","year":"1992","journal-title":"Complexity Analysis of Real-time Reinforcement Learning Applied to Finding Shortest Paths in Deterministic Domains"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref10","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref11","first-page":"118","article-title":"The MAXQ method for hierarchical reinforcement learning","author":"dietterich","year":"1998","journal-title":"Proc 15th Int Conf Mach Learn"},{"key":"ref40","first-page":"9","article-title":"Comparative analysis of abstract policies to transfer learning in robotics navigation","author":"freire","year":"2015","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912472380"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.06.001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2103311"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727651"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2016.00128"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2016.08.009"},{"key":"ref18","first-page":"895","article-title":"Building portable options: Skill transfer in reinforcement learning","volume":"7","author":"konidaris","year":"2007","journal-title":"Proc IJCAI"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.1994.343739"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1037\/h0071363"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1037\/h0071280"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(88)90014-X"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1207\/s15326985ep2402_1"},{"key":"ref8","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref7","author":"thrun","year":"2012","journal-title":"Learning to Learn"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1177\/1059712313511648"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref46","first-page":"83","article-title":"Action monitoring and forward control of movements","author":"jeannerod","year":"2003","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1037\/0097-7403.6.3.207"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SAMI.2014.6822379"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2013.6650435"},{"key":"ref42","first-page":"2","article-title":"Affordances as transferable knowledge for planning agents","author":"barth-maron","year":"2014","journal-title":"Proc AAAI Fall Symp"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2319733"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2012.05.003"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2012.10.038"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8360119\/07902152.pdf?arnumber=7902152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:22:33Z","timestamp":1642004553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7902152\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":65,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2017.2690910","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6]]}}}