{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:03:05Z","timestamp":1740099785320,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T00:00:00Z","timestamp":1604016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T00:00:00Z","timestamp":1604016000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T00:00:00Z","timestamp":1604016000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61773115"],"award-info":[{"award-number":["61773115"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["BK20161427"],"award-info":[{"award-number":["BK20161427"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,30]]},"DOI":"10.1109\/icnsc48988.2020.9238061","type":"proceedings-article","created":{"date-parts":[[2020,11,4]],"date-time":"2020-11-04T21:14:02Z","timestamp":1604524442000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["An Initialization Method of Deep Q-network for Learning Acceleration of Robotic Grasp"],"prefix":"10.1109","author":[{"given":"Yanxu","family":"Hou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihan","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuechao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"0","journal-title":"Foundations and Trends in Robotics"},{"key":"ref11","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref12","article-title":"One-shot imitation learning","author":"duan","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref14","article-title":"A knowledge-based initialization technique of genetic algorithm for the travelling salesman problem","author":"li","year":"0","journal-title":"IEEE Conference on Natural Computation (ICNC)"},{"key":"ref15","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2006.07.013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref18","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems(NIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2018.8560342"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989345"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref8","article-title":"Trust Region Policy Optimization","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50115-4_16"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.016"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461044"},{"key":"ref9","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2018.8560406"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2018.8560458"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462863"}],"event":{"name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","start":{"date-parts":[[2020,10,30]]},"location":"Nanjing, China","end":{"date-parts":[[2020,11,2]]}},"container-title":["2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9238048\/9238049\/09238061.pdf?arnumber=9238061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:14:33Z","timestamp":1656375273000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9238061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,30]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icnsc48988.2020.9238061","relation":{},"subject":[],"published":{"date-parts":[[2020,10,30]]}}}