{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T19:23:05Z","timestamp":1740165785095,"version":"3.37.3"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1109\/tnnls.2018.2869978","type":"journal-article","created":{"date-parts":[[2018,10,10]],"date-time":"2018-10-10T18:44:23Z","timestamp":1539197063000},"page":"1635-1650","source":"Crossref","is-referenced-by-count":9,"title":["Exploiting Generalization in the Subspaces for Faster Model-Based Reinforcement Learning"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6357-3311","authenticated-orcid":false,"given":"Maryam","family":"Hashemzadeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3669-760X","authenticated-orcid":false,"given":"Reshad","family":"Hosseini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6370-6057","authenticated-orcid":false,"given":"Majid Nili","family":"Ahmadabadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"89","article-title":"Near-optimal regret bounds for reinforcement learning","author":"auer","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"49","article-title":"Logarithmic online regret bounds for undiscounted reinforcement learning","author":"ortner","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"article-title":"A developmental method for multimodal sensory integration","year":"2014","author":"daee","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0103143"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2011.2170213"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753712972"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.009"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(00)00047-3"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref28","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref27","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14540"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2000.894638"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9120-4"},{"key":"ref21","first-page":"418","article-title":"Reinforcement learning on an omnidirectional mobile robot","author":"hafner","year":"2003","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref24","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17537-4_27"},{"key":"ref26","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"journal-title":"Deep reinforcement learning in large discrete action spaces","year":"2015","author":"dulac-arnold","key":"ref25"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033442"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900026"},{"journal-title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","year":"2017","author":"nagabandi","key":"ref58"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref55","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in Atari games","author":"oh","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","first-page":"1928","article-title":"DetH*: Approximate Hierarchical Solution of large Markov decision processes","author":"barry","year":"2011","journal-title":"Proc Int Joint Artif Intell Conf"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390238"},{"key":"ref52","first-page":"402","article-title":"Applying reinforcement learning to small scale combat in the real-time strategy game StarCraft: Broodwar","author":"wender","year":"2012","journal-title":"Proc IEEE Conf Comput Intell Games"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cobeha.2015.07.007"},{"key":"ref11","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"},{"journal-title":"Dynamic Programming and Markov Processes","year":"1960","author":"howard","key":"ref40"},{"key":"ref12","first-page":"550","article-title":"Generalization and scaling in reinforcement learning","author":"ackley","year":"1990","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","first-page":"1","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2379-3_11"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15822-3_14"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref16"},{"key":"ref17","first-page":"3338","article-title":"Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning","author":"guo","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2463372.2463509"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008942012299"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2978-14.2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509181"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/3477.979961"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2013.04.010"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"journal-title":"Reinforcement Learning","year":"1997","author":"barto","key":"ref49"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-009-0192-0"},{"journal-title":"Introduction to Probability","year":"2002","author":"bertsekas","key":"ref46"},{"key":"ref45","first-page":"1","article-title":"Efficient planning in MDPs by small backups","author":"van seijen","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"article-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref48"},{"key":"ref47","first-page":"213","article-title":"R-MAX—A general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2002","journal-title":"J Mach Learn Res"},{"article-title":"Inequalities for the $L_{1}$ deviation of the empirical distribution","year":"2003","author":"weissman","key":"ref42"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500830"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058926"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8721184\/08488677.pdf?arnumber=8488677","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,3]],"date-time":"2022-09-03T19:27:23Z","timestamp":1662233243000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8488677\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":59,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2018.2869978","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2019,6]]}}}