{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:19:59Z","timestamp":1759335599021,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/robio.2018.8665248","type":"proceedings-article","created":{"date-parts":[[2019,3,19]],"date-time":"2019-03-19T00:01:56Z","timestamp":1552953716000},"page":"1755-1760","source":"Crossref","is-referenced-by-count":28,"title":["Path Planning of Humanoid Arm Based on Deep Deterministic Policy Gradient"],"prefix":"10.1109","author":[{"given":"Shuhuan","family":"Wen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueheng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3721"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICECCT.2017.8118011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICSEngT.2014.7111783"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23232-9_21"},{"journal-title":"Object Grasping with the NAO[J]","year":"2012","author":"van der wal","key":"ref14"},{"key":"ref15","first-page":"518","article-title":"Human-level control through deep reinforcement learning","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref16","article-title":"Deep Reinforcement Learning with Double Q-learning","author":"hasselt","year":"2015","journal-title":"Computer Science"},{"key":"ref17","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"journal-title":"Asynchronous methods for deep reinforcement learning","year":"2016","author":"mnih","key":"ref18"},{"journal-title":"Distributed Distributional Deterministic Policy Gradients","year":"2018","author":"barthmaron","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014237"},{"key":"ref3","first-page":"523","article-title":"Obstacle avoidance through reinforcement learning","author":"prescott","year":"1991","journal-title":"Proc Int Conf Neural Information Processing Systems"},{"key":"ref6","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Int ConfMachine Learning"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","volume":"8","author":"lillicrap","year":"2015","journal-title":"Computer Science"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2628038"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1166\/asl.2011.1326"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(00)00307-6"},{"key":"ref1","first-page":"149","article-title":"An introduction to stochastic control theory, path integrals and reinforcement learning","author":"kappen","year":"2001","journal-title":"American Institute of Physics Conf Proc"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2013.399"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/34.58871"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-741252-8.50010-8"},{"key":"ref21","first-page":"445","article-title":"Theory of the backpropagation neural network","author":"hecht-nielsen","year":"2002","journal-title":"Proc Int Conf Neural Networks"}],"event":{"name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2018,12,12]]},"location":"Kuala Lumpur, Malaysia","end":{"date-parts":[[2018,12,15]]}},"container-title":["2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8653250\/8664715\/08665248.pdf?arnumber=8665248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T22:53:59Z","timestamp":1598223239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8665248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/robio.2018.8665248","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}