{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T01:20:52Z","timestamp":1776820852819,"version":"3.51.2"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2010,6,1]],"date-time":"2010-06-01T00:00:00Z","timestamp":1275350400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Auton. Mental Dev."],"published-print":{"date-parts":[[2010,6]]},"DOI":"10.1109\/tamd.2010.2051031","type":"journal-article","created":{"date-parts":[[2010,5,28]],"date-time":"2010-05-28T14:40:41Z","timestamp":1275057641000},"page":"70-82","source":"Crossref","is-referenced-by-count":273,"title":["Intrinsically Motivated Reinforcement Learning: An Evolutionary Perspective"],"prefix":"10.1109","volume":"2","author":[{"given":"Satinder","family":"Singh","sequence":"first","affiliation":[]},{"given":"Richard L.","family":"Lewis","sequence":"additional","affiliation":[]},{"given":"Andrew G.","family":"Barto","sequence":"additional","affiliation":[]},{"given":"Jonathan","family":"Sorg","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.2184"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.1652"},{"key":"ref33","author":"schmidhuber","year":"1991","journal-title":"Adaptive Confidence and Adaptive Curiosity"},{"key":"ref32","author":"schmidhuber","year":"1991","journal-title":"Adaptive Confidence and Adaptive Curiosity"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2007.4354052"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1080\/095400900750060131"},{"key":"ref37","author":"schmidhuber","year":"1993","journal-title":"Reinforcement Driven Information Acquisition in Nondeterministic Environments Technical Report"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.1999.785467"},{"key":"ref35","author":"schmidhuber","year":"1997","journal-title":"What's Interesting?"},{"key":"ref34","first-page":"222","article-title":"a possibility for implementing curiosity and boredom in model-building neural controllers","author":"schmidhuber","year":"1991","journal-title":"Proc 3rd Int Conf Simulation of Adaptive Behavior"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1006\/ceps.1999.1020"},{"key":"ref27","first-page":"463","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","author":"randlv","year":"1998","journal-title":"Proc 15th Int Conf Mach Learn"},{"key":"ref29","first-page":"119","article-title":"information, evolution, and utility","volume":"1","author":"samuelson","year":"2006","journal-title":"Economic Theory"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"key":"ref1","first-page":"487","author":"ackley","year":"1991","journal-title":"Artificial Life II"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-2236(03)00177-2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89187-1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-008-5061-y"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1037\/h0058775"},{"key":"ref23","article-title":"policy invariance under reward transformations: theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proc 16th Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.12.006.2007"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2007.4354030"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.09.013"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1037\/h0060312"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1613\/jair.1190","article-title":"potential-based shaping and <formula formulatype=\"inline\"><tex notation=\"tex\">${\\rm q}$<\/tex><\/formula>-value initialization are equivalent","volume":"19","author":"wiewiora","year":"2003","journal-title":"J Artif Intell Res"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref52","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45105-6_62"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/1059712308092835"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051031"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/h0058114"},{"key":"ref13","author":"hull","year":"1943","journal-title":"Principles of Behavior"},{"key":"ref14","author":"hull","year":"1951","journal-title":"Essentials of Behavior"},{"key":"ref15","author":"hull","year":"1952","journal-title":"A Behaviour System An Introduction to Behaviour Theory Concerning the Individual Organism"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"reinforcement learning: a survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"J Artif Intell Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143906"},{"key":"ref18","author":"lenat","year":"1976","journal-title":"AM An Artificial Intelligence Approach to Discovery in Mathematics"},{"key":"ref19","first-page":"136","article-title":"adaptation in constant utility nonstationary environments","author":"littman","year":"1991","journal-title":"Proc 4th Int Conf Genetic Algorithms"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2050205"},{"key":"ref6","author":"cannon","year":"1932","journal-title":"The Wisdom of the Body"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.25"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/11553090_94"},{"key":"ref7","author":"cofer","year":"1964","journal-title":"Motivation Theory and Research"},{"key":"ref49","first-page":"1633","article-title":"transfer learning for reinforcement learning","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-2271-7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273606"},{"key":"ref47","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref42","author":"skinner","year":"1938","journal-title":"The Behavior of Organisms"},{"key":"ref41","first-page":"2601","article-title":"Where do rewards come from?","author":"singh","year":"2009","journal-title":"Proc 15th Annu Conf Cognit Sci Soc"},{"key":"ref44","article-title":"Internal rewards mitigate agent boundedness","author":"sorg","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69134-1_2"}],"container-title":["IEEE Transactions on Autonomous Mental Development"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4563672\/5497035\/05471106.pdf?arnumber=5471106","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T00:45:54Z","timestamp":1633913154000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5471106\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,6]]},"references-count":55,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tamd.2010.2051031","relation":{},"ISSN":["1943-0604","1943-0612"],"issn-type":[{"value":"1943-0604","type":"print"},{"value":"1943-0612","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,6]]}}}