{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:25:54Z","timestamp":1760171154794,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/cis-ram47153.2019.9095849","type":"proceedings-article","created":{"date-parts":[[2020,5,19]],"date-time":"2020-05-19T21:09:55Z","timestamp":1589922595000},"page":"380-385","source":"Crossref","is-referenced-by-count":9,"title":["Trajectory-Tracking Control of Robotic System via Proximal Policy Optimization"],"prefix":"10.1109","author":[{"given":"Shansi","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Yipeng","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Guoqiang","family":"Hu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"year":"2017","author":"schulman","article-title":"Proximal Policy Optimization Algorithms","key":"ref11"},{"year":"2017","author":"heess","article-title":"Emergence of Locomotion Behaviours in Rich Environments","key":"ref12"},{"key":"ref13","article-title":"Massively parallel methods for deep reinforcement learning","author":"nair","year":"2015","journal-title":"International Conference on Machine Learning"},{"year":"0","author":"mnih","article-title":"Asynchronous Methods for Deep Reinforcement Learning","key":"ref14"},{"key":"ref15","article-title":"Distributed Prioritized Experience Replay","author":"horgan","year":"2018","journal-title":"International Conference on Learning Representations"},{"year":"2018","author":"espeholt","article-title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1016\/j.robot.2016.01.002"},{"key":"ref18","article-title":"HighDimensional Continuous Control Using Generalized Advantage Estimation","author":"schulman","year":"2016","journal-title":"International Conference on Learning Representations"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1162\/neco.1997.9.8.1735"},{"year":"2013","author":"mnih","article-title":"Playing Atari with Deep Reinforcement Learning","key":"ref4"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"zhan","year":"2015","journal-title":"Nature"},{"year":"2015","author":"wang","article-title":"Dueling Network Architectures for Deep Reinforcement Learning","key":"ref6"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep Reinforcement Learning with Double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref8","article-title":"Continuous control with deep reinforcement learning","author":"lynch","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11796","article-title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","author":"hessel","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref2","first-page":"119","article-title":"Adaptive SlidingMode Dynamic Control For Path Tracking of Nonholonomic Wheeled Mobile Robot","volume":"9","author":"koubaa","year":"2015","journal-title":"Journal of Automation & Systems Engineering"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"3837","DOI":"10.1007\/s00521-016-2242-7","article-title":"Discrete-time sliding mode neuro-adaptive controller for SCARA robot arm","volume":"28","author":"soria","year":"2017","journal-title":"Neural Computing and Applications"},{"key":"ref9","first-page":"387","article-title":"Deterministic Policy Gradient Algorithms","author":"silver","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref20","first-page":"29","article-title":"Deep Recurrent Q-Learning for Partially Observable MDPs","author":"hausknecht","year":"2015","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1145\/3197517.3201311"},{"key":"ref21","article-title":"The Reactor: A fast and sample-efficient Actor- Critic agent for Reinforcement Learning","author":"evelopment","year":"2018","journal-title":"International Conference on Learning Representations"}],"event":{"name":"2019 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM)","start":{"date-parts":[[2019,11,18]]},"location":"Bangkok, Thailand","end":{"date-parts":[[2019,11,20]]}},"container-title":["2019 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9094049\/9095541\/09095849.pdf?arnumber=9095849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T07:36:01Z","timestamp":1666596961000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9095849\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/cis-ram47153.2019.9095849","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}