{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:13:33Z","timestamp":1730297613480,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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":[[2019,10]]},"DOI":"10.1109\/smc.2019.8914085","type":"proceedings-article","created":{"date-parts":[[2019,11,29]],"date-time":"2019-11-29T15:09:34Z","timestamp":1575040174000},"page":"2543-2548","source":"Crossref","is-referenced-by-count":0,"title":["Sample-Efficient Policy Learning based on Completely Behavior Cloning"],"prefix":"10.1109","author":[{"given":"Qiming","family":"Zou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2013.11.016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3182\/20090916-3-ES-3003.00004"},{"key":"ref10","first-page":"1","article-title":"Guided policy search","volume":"28","author":"levine","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S1874-1029(13)60024-5"},{"key":"ref12","article-title":"State aware imitation learning","author":"schroecker","year":"2017","journal-title":"Advances in Neural Information Processing Systems(NIPS)"},{"key":"ref13","article-title":"Robust imitation of diverse behaviors","author":"wang","year":"2017","journal-title":"Advances in Neural Information Processing Systems(NIPS)"},{"key":"ref14","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"NIPS Deep Learning Workshop"},{"key":"ref15","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref16","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref17","first-page":"1071","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Global convergence of policy gradient methods for linearized control problems","author":"chen","year":"2018","journal-title":"2016 35th Chinese Control Conference"},{"key":"ref19","first-page":"1","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"2017","journal-title":"arXiv preprint arXiv 1707 06892"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00174-1"},{"key":"ref4","article-title":"Proximal policy optimization algorithms","author":"john","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref3","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2015","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","article-title":"Emergence of locomotion behaviours in rich environments","volume":"10668","year":"2018","journal-title":"Mobile Multimedia\/Image Processing Security and Applications"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.10.019"},{"key":"ref5","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017","journal-title":"arXiv preprint arXiv 1707 08040"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2806882"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.patcog.2018.05.014","article-title":"Qingling Deep learning for image-based cancer detection and diagnosis - A survey","volume":"83","author":"zilong","year":"2018","journal-title":"Pattern Recognition"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref9","article-title":"Q-prop: Sample-efficient policy gradient with an offpolicy critic","author":"gu","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref1","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":"ref20","first-page":"661","article-title":"Efficient reductions for imitation learning","author":"ross","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref21","first-page":"3342","author":"kahn","year":"2017","journal-title":"PLATO Policy Learning using Adaptive Trajectory Optimization"},{"key":"ref24","first-page":"661","article-title":"Efficient reductions for imitation learning","volume":"9","author":"stephane","year":"2010","journal-title":"Proceedings of the 13th International Conference on Artificial Intelligence and Statistics"},{"key":"ref23","first-page":"3338","author":"guo","year":"2014","journal-title":"Deep learning for real-time atari game play using offline monte-carlo tree search planning"},{"key":"ref26","first-page":"829","article-title":"Learning complex neural network policies with trajectory optimization","author":"levine","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref25","article-title":"Learning deep control policies for autonomous aerial vehicles with mpcguided policy search","author":"zhang","year":"0","journal-title":"Proceedings of IEEE International Conference on Robotics and Automation"}],"event":{"name":"2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)","start":{"date-parts":[[2019,10,6]]},"location":"Bari, Italy","end":{"date-parts":[[2019,10,9]]}},"container-title":["2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8906183\/8913838\/08914085.pdf?arnumber=8914085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T15:21:58Z","timestamp":1658157718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8914085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/smc.2019.8914085","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}