{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T17:55:09Z","timestamp":1768413309445,"version":"3.49.0"},"reference-count":23,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T00:00:00Z","timestamp":1456790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-13-1-0142"],"award-info":[{"award-number":["FA9550-13-1-0142"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Intell. AI Games"],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/tciaig.2014.2369345","type":"journal-article","created":{"date-parts":[[2014,11,10]],"date-time":"2014-11-10T19:34:30Z","timestamp":1415648070000},"page":"56-66","source":"Crossref","is-referenced-by-count":21,"title":["Reinforcement Learning in Video Games Using Nearest Neighbor Interpolation and Metric Learning"],"prefix":"10.1109","volume":"8","author":[{"given":"Matthew S.","family":"Emigh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evan G.","family":"Kriminger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Austin J.","family":"Brockmeier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose C.","family":"Principe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Panos M.","family":"Pardalos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"206","author":"gabel","year":"2005","journal-title":"Case-based Reasoning for State Value Function Approximation in Reinforcement Learning"},{"key":"ref11","article-title":"Covert perceptual capability develop","author":"huang","year":"2005","journal-title":"International Workshop on Epigenetic Robotics"},{"key":"ref12","first-page":"1243","article-title":"Automatic state abstraction from demonstration","volume":"22","author":"cobo","year":"2011","journal-title":"Proc Int Joint Conf Artif Intell IJCAI"},{"key":"ref13","first-page":"48 109","article-title":"Using imagery to simplify perceptual abstraction in reinforcement learning agents","volume":"1001","author":"wintermute","year":"2010","journal-title":"Proc AAAI Nat Conf Artificial Intell"},{"key":"ref14","article-title":"Metric learning for invariant feature generation in reinforcement learning","author":"kriminger","year":"2013","journal-title":"Multidisciplinary Conf on Reinforcement Learning and Decision Making"},{"key":"ref15","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref17","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"NIPS Deep Learning Workshop 2013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.1.72"},{"key":"ref19","first-page":"505","author":"xing","year":"2003","journal-title":"Advances Neural Inform Processing Syst"},{"key":"ref4","author":"thrun","year":"1995","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref6","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007634325138"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/153244303322753616"},{"key":"ref2","first-page":"15","article-title":"Neuro-dynamic programming (optimization and neural computation series, 3)","volume":"7","author":"bertsekas","year":"1996","journal-title":"Athena Scientific"},{"key":"ref1","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","author":"gordon","year":"1995","journal-title":"?Stable function approximation in dynamic programming DTIC Document ?"},{"key":"ref20","first-page":"73","article-title":"Dimensionality reduction for supervised learning with reproducing kernel Hilbert spaces","volume":"5","author":"fukumizu","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref22","first-page":"795","article-title":"Algorithms for learning kernels based on centered alignment","volume":"13","author":"cortes","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00591"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/11564089_7"}],"container-title":["IEEE Transactions on Computational Intelligence and AI in Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4804728\/7434093\/06951334.pdf?arnumber=6951334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:28:28Z","timestamp":1642004908000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6951334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":23,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tciaig.2014.2369345","relation":{},"ISSN":["1943-068X","1943-0698"],"issn-type":[{"value":"1943-068X","type":"print"},{"value":"1943-0698","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,3]]}}}