{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T04:22:48Z","timestamp":1754108568009,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"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":[[2019,8]]},"DOI":"10.1109\/rcar47638.2019.9043970","type":"proceedings-article","created":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T03:20:28Z","timestamp":1585020028000},"page":"803-808","source":"Crossref","is-referenced-by-count":4,"title":["Accomplishing Robot Grasping Task Rapidly via Adversarial Training"],"prefix":"10.1109","author":[{"given":"Guoyu","family":"zuo","sequence":"first","affiliation":[]},{"given":"Jiahao","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Kexin","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jianjun","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Xiangsheng","family":"Huang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"5320","article-title":"Robust imitation of diverse behaviors","author":"wang","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref12"},{"journal-title":"Emergence of locomotion behaviours in rich environments","year":"2017","author":"heess","key":"ref13"},{"key":"ref14","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"ICML"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref15"},{"journal-title":"Multi-goal reinforcement learning Challenging robotics environments and request for research","year":"2018","author":"plappert","key":"ref16"},{"journal-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref17"},{"key":"ref18","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref3","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","volume":"abs 1707 8817","author":"vecer\u00edk","year":"2017","journal-title":"CoRR"},{"key":"ref6","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2016.06.003"},{"key":"ref8","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Deep q-learning from demonstrations","author":"hester","year":"0","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"journal-title":"Third-person imitation learning","year":"2017","author":"stadie","key":"ref9"}],"event":{"name":"2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)","start":{"date-parts":[[2019,8,4]]},"location":"Irkutsk, Russia","end":{"date-parts":[[2019,8,9]]}},"container-title":["2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9034064\/9043918\/09043970.pdf?arnumber=9043970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:13:45Z","timestamp":1657854825000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9043970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/rcar47638.2019.9043970","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}