{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T12:54:05Z","timestamp":1730292845701,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"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":[[2022,12,5]]},"DOI":"10.1109\/robio55434.2022.10011646","type":"proceedings-article","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T18:51:38Z","timestamp":1674067898000},"page":"1445-1450","source":"Crossref","is-referenced-by-count":1,"title":["Research on Learning from Demonstration System of Manipulator Based on the Improved Soft Actor-Critic Algorithm"],"prefix":"10.1109","author":[{"given":"Ze","family":"Cui","sequence":"first","affiliation":[{"name":"School of Mechatronic Engineering and Automation, Shanghai University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering and Automation, Shanghai University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zenghao","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Aerospace Control Technology Institute,Shanghai,China,201109"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Bao","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering and Automation, Shanghai University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lang","family":"Kou","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering and Automation, Shanghai University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lang","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering and Automation, Shanghai University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering and Automation, Shanghai University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danjie","family":"Zhu","sequence":"additional","affiliation":[{"name":"Orthopedics, Zhejiang Provincial People's Hospital,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"03","key":"ref1","first-page":"458","article-title":"A Survey of Methods for Learning Robot Manipulation Skills","volume":"45","author":"Liu","year":"2019","journal-title":"Acta Automatica Sinica"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2012.28"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152577"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794062"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918784350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630809"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28872-7_20"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICARSC.2015.27"},{"key":"ref10","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on Robot Learning","author":"Kalashnikov"},{"key":"ref11","first-page":"767","article-title":"SURREAL: Open-source reinforcement learning framework and robot manipulation benchmark","volume-title":"Conference on Robot Learning","author":"Fan"},{"key":"ref12","first-page":"1279","article-title":"Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration","volume-title":"Conference on Robot Learning","author":"Wang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636023"},{"key":"ref14","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International Conference on Machine Learning","author":"Fujimoto"},{"key":"ref16","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref18","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","author":"Ziebart","year":"2008","journal-title":"Aaai"},{"key":"ref19","article-title":"Maximum entropy deep inverse reinforcement learning","author":"Wulfmeier","year":"2015","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"International Conference on Machine Learning","author":"Finn"},{"key":"ref21","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","author":"Ross"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref23","first-page":"720","article-title":"Learning and Transferring Action Schemas","volume-title":"20th International Joint Conference on Artificial Intelligence","author":"Cohen","year":"2007"}],"event":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2022,12,5]]},"location":"Jinghong, China","end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10011626\/10011636\/10011646.pdf?arnumber=10011646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T07:56:42Z","timestamp":1707465402000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10011646\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/robio55434.2022.10011646","relation":{},"subject":[],"published":{"date-parts":[[2022,12,5]]}}}