{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:57:19Z","timestamp":1784822239541,"version":"3.55.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/smc.2017.8122622","type":"proceedings-article","created":{"date-parts":[[2017,11,30]],"date-time":"2017-11-30T22:22:47Z","timestamp":1512080567000},"page":"316-321","source":"Crossref","is-referenced-by-count":219,"title":["A novel DDPG method with prioritized experience replay"],"prefix":"10.1109","author":[{"given":"Yuenan","family":"Hou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lifeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xudong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nn.3843"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"ref12","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref13","first-page":"3014","article-title":"Weighted importance sampling for off-policy learning with linear function approximation","author":"mahmood","year":"2014","journal-title":"Proc of International Conference on Neural Information Processing"},{"key":"ref14","article-title":"Prioritized Experience Replay","author":"schaul","year":"2016","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref15","author":"abadi","year":"2016","journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems"},{"key":"ref16","article-title":"TensorFlow: A system for largescale machine learning","author":"abadi","year":"2016","journal-title":"Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI'02)"},{"key":"ref17","article-title":"OpenAI Gym","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref18","author":"ioffe","year":"2015","journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift"},{"key":"ref19","author":"kingma","year":"2017","journal-title":"Adam A method for stochastic optimization"},{"key":"ref4","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref3","first-page":"387","article-title":"Deterministic Policy Gradient Algorithms","author":"silver","year":"2014","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref6","first-page":"3338","article-title":"Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning","author":"guo","year":"2014","journal-title":"Proc of International Conference on Neural Information Processing"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"ref7","article-title":"Reinforcement learning for robots using neural networks","author":"lin","year":"1993","journal-title":"Carnegie Mellon University"},{"key":"ref2","first-page":"2944","article-title":"Learning continuous control policies by stochastic value gradients","author":"heess","year":"2015","journal-title":"Proc of International Conference on Neural Information Processing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2009.11.016"},{"key":"ref1","first-page":"187a","article-title":"Continuous control with deep reinforcement learning","volume":"8","author":"lillicrap","year":"2016","journal-title":"Computer Science"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref22","first-page":"4397","article-title":"Simulation tools for model-based robotics: Comparison of Bullet, Havok, MuJoCo, ODE and PhysX","author":"todorov","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Robotics and Automation"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574705002596"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/11539117_97"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2283574"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.925743"}],"event":{"name":"2017 IEEE International Conference on Systems, Man and Cybernetics (SMC)","location":"Banff, AB","start":{"date-parts":[[2017,10,5]]},"end":{"date-parts":[[2017,10,8]]}},"container-title":["2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8114675\/8122565\/08122622.pdf?arnumber=8122622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,1,17]],"date-time":"2018-01-17T23:15:46Z","timestamp":1516230946000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8122622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/smc.2017.8122622","relation":{},"subject":[],"published":{"date-parts":[[2017,10]]}}}