{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:24:55Z","timestamp":1730265895486,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/ijcnn.2019.8852307","type":"proceedings-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T03:44:32Z","timestamp":1569901472000},"page":"1-8","source":"Crossref","is-referenced-by-count":8,"title":["Adversarial Imitation Learning via Random Search"],"prefix":"10.1109","author":[{"given":"MyungJae","family":"Shin","sequence":"first","affiliation":[]},{"given":"Joongheon","family":"Kim","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Openai baselines","year":"2017","author":"dhariwal","key":"ref32"},{"article-title":"Openai gym","year":"2016","author":"brockman","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref11"},{"article-title":"Deep reinforcement learning that matters","year":"2017","author":"henderson","key":"ref12"},{"article-title":"Reproducibility of benchmarked deep reinforcement learning tasks for continuous control","year":"2017","author":"islam","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"ref15","first-page":"429","article-title":"Rapidly adapting artificial neural networks for autonomous navigation","author":"pomerleau","year":"1991","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Evolution strategies as a scalable alternative to reinforcement learning","year":"2017","author":"salimans","key":"ref18"},{"key":"ref19","first-page":"6550","article-title":"Towards generalization and simplicity in continuous control","author":"rajeswaran","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref3","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","year":"2015","author":"abadi","key":"ref29"},{"article-title":"Distributed prioritized experience replay","year":"2018","author":"horgan","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_18"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref2","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning"},{"article-title":"Dexterous manipulation with deep reinforcement learning: Efficient, general, and low-cost","year":"2018","author":"zhu","key":"ref9"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref1"},{"article-title":"Simple random search provides a competitive approach to reinforcement learning","year":"2018","author":"mania","key":"ref20"},{"article-title":"Optiongan: Learning joint reward-policy options using generative adversarial inverse reinforcement learning","year":"2017","author":"henderson","key":"ref22"},{"journal-title":"Submitted to Int Conf Learning Representations","article-title":"Generative adversarial self-imitation learning","year":"2019","key":"ref21"},{"key":"ref24","article-title":"Random gradient-free minimization of convex functions","author":"nesterov","year":"2011","journal-title":"Université catholique de Louvain Center for Operations Research and Econometrics (CORE) Tech Rep"},{"key":"ref23","first-page":"246","article-title":"Random optimization","volume":"26","author":"matyas","year":"1965","journal-title":"Automation and Remote Control"},{"key":"ref26","first-page":"2190","article-title":"Reward design via online gradient ascent","author":"sorg","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref25","first-page":"385","article-title":"Online convex optimization in the bandit setting: gradient descent without a gradient","author":"flaxman","year":"2005","journal-title":"Proceedings of the Sixteenth Annual ACM-SIAM Symposium on Discrete Algorithms Society for Industrial and Applied Mathematics"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2019,7,14]]},"location":"Budapest, Hungary","end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8840768\/8851681\/08852307.pdf?arnumber=8852307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:51:27Z","timestamp":1658094687000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8852307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8852307","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}