{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:30:28Z","timestamp":1771702228970,"version":"3.50.1"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T00:00:00Z","timestamp":1604016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T00:00:00Z","timestamp":1604016000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T00:00:00Z","timestamp":1604016000000},"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":[[2020,10,30]]},"DOI":"10.1109\/icnsc48988.2020.9238129","type":"proceedings-article","created":{"date-parts":[[2020,11,4]],"date-time":"2020-11-04T21:14:02Z","timestamp":1604524442000},"page":"1-6","source":"Crossref","is-referenced-by-count":14,"title":["An Overview of Robust Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Shiyu","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yanjie","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"839","article-title":"Robustness in markov decision problems with uncertain transition matrices","author":"nilim","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"ref38","first-page":"701","article-title":"Reinforcement learning in robust markov decision processes","author":"lim","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref32","first-page":"799","article-title":"Autonomous helicopter flight via reinforcement learning","author":"ng","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Torcs, the open racing car simulator","volume":"4","author":"wymann","year":"2000","journal-title":"Software Available"},{"key":"ref30","author":"tassa","year":"2018","journal-title":"Deepmind control suite"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2016.0786"},{"key":"ref36","first-page":"233","article-title":"Robustness and risk-sensitivity in markov decision processes","author":"osogami","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2930489"},{"key":"ref34","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","author":"abbeel","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref10","author":"polvara","year":"2017","journal-title":"Autonomous Quadrotor Landing using Deep Reinforcement Learning"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1120.1641"},{"key":"ref11","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning 2011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref13","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref14","author":"schulman","year":"2017","journal-title":"Proxi-mal Policy Optimization Algorithms"},{"key":"ref15","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref16","first-page":"1889","article-title":"Trust region policy optimization","volume":"3","author":"schulman","year":"2015","journal-title":"32nd International Conference on Machine Learning ICML 2015"},{"key":"ref17","first-page":"605","article-title":"Deterministic policy gradient algorithms","volume":"1","author":"silver","year":"2014","journal-title":"31st International Conference on Machine Learning ICML 2014"},{"key":"ref18","author":"schaul","year":"2015","journal-title":"Prioritized experience replay"},{"key":"ref19","first-page":"3215","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"32nd AAAI Conference on Artificial Intelligence AAAI 2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref4","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref27","author":"derman","year":"2018","journal-title":"Soft-robust actor-critic policy-gradient"},{"key":"ref3","author":"kaiser","year":"2019","journal-title":"Model-based reinforcement learning for atari"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref29","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.11"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/685"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref46","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70 JMLR org"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1257\/aer.91.2.60"},{"key":"ref22","author":"van hasselt","year":"2019","journal-title":"When to use parametric models in reinforcement learning?"},{"key":"ref47","author":"smirnova","year":"2019","journal-title":"Distributionally robust reinforcement learning"},{"key":"ref21","author":"ke","year":"2019","journal-title":"Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future"},{"key":"ref42","first-page":"1537","article-title":"The robustness-performance tradeoff in markov decision processes","author":"xu","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1050.0216"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1080.0685"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref44","author":"abdullah","year":"2019","journal-title":"Wasserstein robust reinforcement learning"},{"key":"ref26","author":"mankowitz","year":"2019","journal-title":"Robust Reinforcement Learning for Continuous Control with Model Misspecification"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/BF00532240"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0129"}],"event":{"name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","location":"Nanjing, China","start":{"date-parts":[[2020,10,30]]},"end":{"date-parts":[[2020,11,2]]}},"container-title":["2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9238048\/9238049\/09238129.pdf?arnumber=9238129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:14:33Z","timestamp":1656375273000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9238129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,30]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icnsc48988.2020.9238129","relation":{},"subject":[],"published":{"date-parts":[[2020,10,30]]}}}