{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T20:59:32Z","timestamp":1773521972031,"version":"3.50.1"},"reference-count":27,"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\/humanoids43949.2019.9034991","type":"proceedings-article","created":{"date-parts":[[2020,3,17]],"date-time":"2020-03-17T04:35:02Z","timestamp":1584419702000},"page":"274-280","source":"Crossref","is-referenced-by-count":18,"title":["Generative Adversarial Imitation Learning with Deep P-Network for Robotic Cloth Manipulation"],"prefix":"10.1109","author":[{"given":"Yoshihisa","family":"Tsurumine","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunduan","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kimitoshi","family":"Yamazaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509336"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9481.003.0013"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2013.777012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139990"},{"key":"ref15","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Association for the Advancement of Artificial Intelligence (AAAI'05)"},{"key":"ref16","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref18","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecerik","year":"2017","journal-title":"Computing Research Repository (CoRR) abs\/1707 08817"},{"key":"ref19","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2602376"},{"key":"ref27","first-page":"119","article-title":"Dynamic policy programming with function approximation","author":"azar","year":"2011","journal-title":"International Conference on Artificial Intelligence and Statistics (AISTATS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911430417"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41778-3_2"},{"key":"ref5","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2633383"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800122"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2017.1285722"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.11.004"},{"key":"ref20","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref22","article-title":"Variational discriminator bottleneck: Improving imitation learning, inverse RL, and GANs by constraining information flow","author":"peng","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref21","article-title":"Learning human behaviors from motion capture by adversarial imitation","author":"merel","year":"2017","journal-title":"arXiv preprint arXiv 1707 06892"},{"key":"ref24","article-title":"Gotta Learn Fast: A New Benchmark for Generalization in RL","author":"nichol","year":"0","journal-title":"arXiv preprint arXiv 1804 03720 2018"},{"key":"ref23","article-title":"Maximum causal tsallis entropy imitation learning","author":"lee","year":"2018","journal-title":"arXiv preprint arXiv 1805 08336"},{"key":"ref26","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","author":"haarnoja","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref25","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"}],"event":{"name":"2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids)","location":"Toronto, ON, Canada","start":{"date-parts":[[2019,10,15]]},"end":{"date-parts":[[2019,10,17]]}},"container-title":["2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9023508\/9034989\/09034991.pdf?arnumber=9034991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T15:21:18Z","timestamp":1658157678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9034991\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/humanoids43949.2019.9034991","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}