{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T22:18:52Z","timestamp":1769725132134,"version":"3.49.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T00:00:00Z","timestamp":1602115200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T00:00:00Z","timestamp":1602115200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T00:00:00Z","timestamp":1602115200000},"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":[[2020,10,8]]},"DOI":"10.1109\/icstcc50638.2020.9259716","type":"proceedings-article","created":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T00:00:37Z","timestamp":1606176037000},"page":"92-97","source":"Crossref","is-referenced-by-count":19,"title":["Brief Survey of Model-Based Reinforcement Learning Techniques"],"prefix":"10.1109","author":[{"given":"Constantin-Valentin","family":"Pal","sequence":"first","affiliation":[]},{"given":"Florin","family":"Leon","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref38","article-title":"CS 285: Deep Reinforcement Learning, Decision Making, and Control","author":"levine","year":"2019"},{"key":"ref33","first-page":"8224","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","author":"buckman","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"Model-based value estimation for efficient model-free reinforcement learning","author":"feinberg","year":"2018","journal-title":"arXiv preprint arXiv 1803 00101"},{"key":"ref31","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","author":"parisotto","year":"2015","journal-title":"arXiv preprint arXiv 1511 06841"},{"key":"ref30","article-title":"Generative adversarial networks for model based reinforcement learning with tree search","author":"xiao","year":"2016","journal-title":"Technical Report"},{"key":"ref37","first-page":"2154","article-title":"Value iteration networks","author":"tamar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref36","article-title":"Learning model-based planning from scratch","author":"pascanu","year":"2017","journal-title":"arXiv preprint arXiv 1707 07816"},{"key":"ref35","article-title":"Imagination-augmented agents for deep reinforcement learning","author":"weber","year":"2017","journal-title":"arXiv preprint arXiv 1707 06892"},{"key":"ref34","article-title":"Algorithmic framework for model-based deep reinforcement learning with theoretical guarantees","author":"luo","year":"2018","journal-title":"arXiv preprint arXiv 1807 03858"},{"key":"ref28","article-title":"Weight uncertainty in neural networks","author":"blundell","year":"2015","journal-title":"arXiv preprint arxiv 1505 05901"},{"key":"ref27","first-page":"465","article-title":"Pilco: A model-based and data-effcient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref29","first-page":"3581","article-title":"Concrete drop-out","author":"gal","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"arXiv preprint arXiv 1802 01561"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref20","article-title":"Exploring model-based planning with policy networks","author":"wang","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref21","article-title":"Dynamics-aware unsupervised discovery of skills","author":"sharma","year":"2019","journal-title":"arXiv preprint arXiv 1907 09977"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5280-0"},{"key":"ref23","article-title":"The cma evolution strategy: A tutorial","author":"hansen","year":"2016","journal-title":"arXiv preprint arXiv 1604 00772"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1080\/00207178808906114"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5106-x"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref51","article-title":"A survey of deep reinforcement learning in video games","author":"shao","year":"2019","journal-title":"arXiv preprint arXiv 1912 10944"},{"key":"ref10","article-title":"Benchmarking model-based reinforcement learning","author":"langlois","year":"0","journal-title":"arXiv preprint arXiv 1907 09977"},{"key":"ref11","article-title":"Model-ensemble trust-region policy optimization","author":"kurutach","year":"2018","journal-title":"arXiv preprint arXiv 1802 10363"},{"key":"ref40","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref12","article-title":"Model-based reinforcement learning via meta-policy optimization","author":"clavera","year":"2018","journal-title":"arXiv preprint arXiv 1809 05214"},{"key":"ref13","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"A modified I2A agent for learning in a stochastic environment","author":"pal","year":"2020","journal-title":"Proceedings of the ICCCI 2020 Da Nang Vietnam nov 2020"},{"key":"ref15","article-title":"World models","author":"ha","year":"2018","journal-title":"arXiv preprint arXiv 1803 10122"},{"key":"ref16","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref17","article-title":"Mastering atari, go, chess and shogi by planning with a learned model","author":"schrittwieser","year":"2019","journal-title":"arXiv preprint arXiv 1911 12945"},{"key":"ref18","first-page":"497","article-title":"A survey of numerical methods for optimal control","volume":"135","author":"rao","year":"2009","journal-title":"Advances in the Astronautical Sciences"},{"key":"ref19","article-title":"Robust constrained model predictive control","author":"richards","year":"2005","journal-title":"PhD thesis"},{"key":"ref4","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"arXiv preprint arXiv 1803 00933"},{"key":"ref3","article-title":"Recurrent experience replay in distributed reinforcement learning","author":"kapturowski","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref6","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"silver","year":"2017","journal-title":"arXiv preprint arXiv 1712 01815"},{"key":"ref5","article-title":"Agent57: Outperforming the atari human benchmark","author":"badia","year":"2020","journal-title":"arXiv preprint arXiv 2003 13874"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/880"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2958211"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref45","article-title":"Model-based reinforcement learning for atari","author":"kaiser","year":"2019","journal-title":"arXiv preprint arXiv 1903 00066"},{"key":"ref48","article-title":"Model-based reinforcement learning: A survey","author":"yi","year":"2018"},{"key":"ref47","article-title":"Deep reinforcement learning: An overview","author":"li","year":"2017","journal-title":"arXiv preprint arXiv 1701 07717"},{"key":"ref42","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref43","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","author":"janner","year":"2019","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2020 24th International Conference on System Theory, Control and Computing (ICSTCC)","location":"Sinaia, Romania","start":{"date-parts":[[2020,10,8]]},"end":{"date-parts":[[2020,10,10]]}},"container-title":["2020 24th International Conference on System Theory, Control and Computing (ICSTCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9259608\/9259629\/09259716.pdf?arnumber=9259716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:11:09Z","timestamp":1656375069000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9259716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,8]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/icstcc50638.2020.9259716","relation":{},"subject":[],"published":{"date-parts":[[2020,10,8]]}}}