{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:59:21Z","timestamp":1783061961891,"version":"3.54.6"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T00:00:00Z","timestamp":1624838400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T00:00:00Z","timestamp":1624838400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100008192","name":"Automotive Research Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008192","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006751","name":"U.S. Army","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006751","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,28]]},"DOI":"10.1109\/cec45853.2021.9505001","type":"proceedings-article","created":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T21:57:06Z","timestamp":1628546226000},"page":"2077-2084","source":"Crossref","is-referenced-by-count":5,"title":["Behavioral Cloning in Atari Games Using a Combined Variational Autoencoder and Predictor Model"],"prefix":"10.1109","author":[{"given":"Brian","family":"Chen","sequence":"first","affiliation":[{"name":"University of Michigan,Department of Mathematics,Ann Arbor,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siddhant","family":"Tandon","sequence":"additional","affiliation":[{"name":"University of Michigan,Department of Aerospace Engineering,Ann Arbor,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Gorsich","sequence":"additional","affiliation":[{"name":"Ground Vehicle Systems Center U.S. Army DEVCOM,Warren,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Gorodetsky","sequence":"additional","affiliation":[{"name":"University of Michigan,Department of Aerospace Engineering,Ann Arbor,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shravan","family":"Veerapaneni","sequence":"additional","affiliation":[{"name":"University of Michigan,Department of Mathematics,Ann Arbor,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0"},{"key":"ref11","article-title":"Robust imitation of diverse behaviors","volume":"30","author":"wang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"1165","article-title":"Safe imitation learning via fast bayesian reward inference from preferences","author":"brown","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref13","article-title":"Rl baselines zoo","author":"raffin","year":"2018"},{"key":"ref14","article-title":"Stable baselines","author":"hill","year":"2018"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0"},{"key":"ref18","article-title":"SGDR: stochastic gradient descent with warm restarts","author":"loshchilov","year":"0"},{"key":"ref4","article-title":"Enhanced behavioral cloning based self-driving car using transfer learning","author":"sumanth","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)46716-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/339"},{"key":"ref5","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proc Seventh Int Conf Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6161"},{"key":"ref7","article-title":"The atari grand challenge dataset","author":"kurin","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/dsd.2020.333"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231600"}],"event":{"name":"2021 IEEE Congress on Evolutionary Computation (CEC)","location":"Krak\u00f3w, Poland","start":{"date-parts":[[2021,6,28]]},"end":{"date-parts":[[2021,7,1]]}},"container-title":["2021 IEEE Congress on Evolutionary Computation (CEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9504682\/9504683\/09505001.pdf?arnumber=9505001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,3]],"date-time":"2022-06-03T19:48:35Z","timestamp":1654285715000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9505001\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,28]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/cec45853.2021.9505001","relation":{},"subject":[],"published":{"date-parts":[[2021,6,28]]}}}