{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:12:36Z","timestamp":1730297556448,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1109\/smc.2019.8913930","type":"proceedings-article","created":{"date-parts":[[2019,11,29]],"date-time":"2019-11-29T15:09:34Z","timestamp":1575040174000},"page":"2899-2906","source":"Crossref","is-referenced-by-count":0,"title":["MDP Autoencoder"],"prefix":"10.1109","author":[{"given":"Sourabh","family":"Bose","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manfred","family":"Huber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/700"},{"key":"ref11","first-page":"1649","article-title":"Bounding performance loss in approximate mdp homomorphisms","author":"taylor","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"124","article-title":"Model reduction techniques for computing approximately optimal solutions for markov decision processes","author":"dean","year":"1997","journal-title":"Proceedings of the thirteenth Conference on Uncertainty in Artificial Intelligence"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2009.5345891"},{"key":"ref14","first-page":"22","article-title":"A dynamic hierarchical task transfer in multiple robot explorations","author":"asadi","year":"2015","journal-title":"Proceedings of the International Conference on Artificial Intelligence"},{"key":"ref15","first-page":"530","article-title":"Decision tree methods for finding reusable mdp homomorphisms","volume":"21","author":"wolfe","year":"1999","journal-title":"Proceedings of the National Conference on Artificial Intelligence"},{"key":"ref16","first-page":"494","article-title":"Using homomorphisms to transfer options across continuous reinforcement learning domains","volume":"6","author":"soni","year":"2006","journal-title":"AAAI"},{"key":"ref17","first-page":"2899","article-title":"Basis refinement strategies for linear value function approximation in mdps","author":"comanici","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"larsen","year":"2015","journal-title":"arXiv preprint arXiv 1512 09300"},{"key":"ref19","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"arXiv preprint arXiv 1312 6114"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref4"},{"key":"ref3","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2018","journal-title":"arXiv preprint arXiv 1811 04551"},{"key":"ref6","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in atari games","author":"oh","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2056368"},{"journal-title":"Approximate homomorphisms A framework for non-exact minimization in markov decision processes","year":"2004","author":"ravindran","key":"ref8"},{"key":"ref7","first-page":"1771","article-title":"Video pixel networks","author":"kalchbrenner","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref2","first-page":"2746","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref1","article-title":"Model-based reinforcement learning for atari","author":"kaiser","year":"2019","journal-title":"arXiv preprint arXiv 1903 00066"},{"key":"ref9","first-page":"6118","article-title":"Value prediction network","author":"oh","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016","journal-title":"arXiv preprint arXiv 1611 01144"},{"key":"ref21","volume":"33","author":"gumbel","year":"1954","journal-title":"Statistical Theory of Extreme Values and Some Practical Applications A Series of Lectures"},{"key":"ref24","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"},{"key":"ref23","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"}],"event":{"name":"2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)","start":{"date-parts":[[2019,10,6]]},"location":"Bari, Italy","end":{"date-parts":[[2019,10,9]]}},"container-title":["2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8906183\/8913838\/08913930.pdf?arnumber=8913930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T15:16:09Z","timestamp":1658157369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8913930\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/smc.2019.8913930","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}