{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T06:48:14Z","timestamp":1729666094470,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,9]]},"DOI":"10.1109\/mlsp.2015.7324371","type":"proceedings-article","created":{"date-parts":[[2015,11,12]],"date-time":"2015-11-12T18:09:32Z","timestamp":1447351772000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["A model based approach to exploration of continuous-state MDPs using Divergence-to-Go"],"prefix":"10.1109","author":[{"given":"Matthew","family":"Emigh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evan","family":"Kriminger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose C.","family":"Principe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Decision-theoretic planning: Structural assumptions and computational leverage","author":"boutilier","year":"2011","journal-title":"arXiv preprint arXiv 1105 5460"},{"key":"ref11","volume":"9","author":"deisenroth","year":"2010","journal-title":"Efficient Reinforcement Learning Using Gaussian Processes"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329242"},{"key":"ref13","first-page":"265","article-title":"Information theoretic learning","volume":"1","author":"principe","year":"2000","journal-title":"Unsupervised Adaptive Filtering"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref15","first-page":"213","article-title":"R-max-a general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref16","first-page":"150","article-title":"Model based bayesian exploration","author":"dearden","year":"1999","journal-title":"Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-1452-1_19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2011.6064634"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1609\/icaps.v19i1.13363","article-title":"Lower bounding klondike solitaire with monte-carlo planning","author":"bjarnason","year":"2009","journal-title":"ICAPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2009.01.016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref6","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87987-9_14"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-017-2053-3_3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_4"},{"journal-title":"Multi-armed Bandit Allocation Indices","year":"1989","author":"gittins","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"ref9","first-page":"717","article-title":"Generalized model learning for reinforcement learning in factored domains","author":"hester","year":"2009","journal-title":"Proceedings of the 8th International Conference on Autonomous Agents and Multiagent Systems-Volume 2"},{"journal-title":"Introduction to Reinforcement Learning","year":"1998","author":"sutton","key":"ref20"},{"key":"ref21","article-title":"On-line q-learning using connectionist systems","author":"rummery","year":"1994","journal-title":"Tech Rep"}],"event":{"name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","start":{"date-parts":[[2015,9,17]]},"location":"Boston, MA, USA","end":{"date-parts":[[2015,9,20]]}},"container-title":["2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7311793\/7324166\/07324371.pdf?arnumber=7324371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T17:03:25Z","timestamp":1692119005000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7324371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/mlsp.2015.7324371","relation":{},"subject":[],"published":{"date-parts":[[2015,9]]}}}