{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:14:13Z","timestamp":1780766053915,"version":"3.54.1"},"reference-count":24,"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\/rcar47638.2019.9043958","type":"proceedings-article","created":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T03:20:28Z","timestamp":1585020028000},"page":"458-463","source":"Crossref","is-referenced-by-count":6,"title":["Actor-Critic Method-Based Search Strategy for High Precision Peg-in-Hole Tasks"],"prefix":"10.1109","author":[{"given":"Zichen","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiansheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haopeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunjiang","family":"Lou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932611"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CoASE.2012.6386340"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1243\/PIME_PROC_1993_207_134_02"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/276264"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1994.351117"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-3615(97)00015-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1115\/1.4026084"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CARE.2013.6733716"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3795\/KSME-A.2011.35.4.347"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1108\/IR-07-2014-0363"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2014.10.077"},{"key":"ref8","first-page":"1071","article-title":"Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics[C]","author":"levine","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1115\/1.4004497"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1108\/AA-11-2015-104"},{"key":"ref9","first-page":"135","article-title":"What is The Remote Centre Compliance (RCC) and What Can It Do?[C]","author":"whitney","year":"0","journal-title":"Proceedings of the 9th International Symposium on Industrial Robots"},{"key":"ref20","first-page":"1889","article-title":"Trust Region Policy Optimization[C]\/\/","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref21","first-page":"1008","article-title":"Actor-critic Algorithms[C]","author":"konda","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"1471","article-title":"Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning[J]","volume":"5","author":"greensmith","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref23","first-page":"1057","article-title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation[C]\/\/","author":"sutton","year":"0","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)","location":"Irkutsk, Russia","start":{"date-parts":[[2019,8,4]]},"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\/09043958.pdf?arnumber=9043958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:12:15Z","timestamp":1657854735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9043958\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/rcar47638.2019.9043958","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}