{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:13:36Z","timestamp":1771467216370,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T00:00:00Z","timestamp":1700524800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T00:00:00Z","timestamp":1700524800000},"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":[[2023,11,21]]},"DOI":"10.1109\/m2vip58386.2023.10413400","type":"proceedings-article","created":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T13:28:38Z","timestamp":1706880518000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Application and Evaluation of Soft-Actor Critic Reinforcement Learning in Constrained Trajectory Planning for 6DOF Robotic Manipulators"],"prefix":"10.1109","author":[{"given":"Wanqing","family":"Xia","sequence":"first","affiliation":[{"name":"The University of Auckland,Mechanical and Mechatronics Engineering,Auckland,New Zealand"}]},{"given":"Yuqian","family":"Lu","sequence":"additional","affiliation":[{"name":"The University of Auckland,Mechanical and Mechatronics Engineering,Auckland,New Zealand"}]},{"given":"Xun","family":"Xu","sequence":"additional","affiliation":[{"name":"The University of Auckland,Mechanical and Mechatronics Engineering,Auckland,New Zealand"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2020.06.010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197508"},{"key":"ref6","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","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref9","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","volume-title":"International conference on machine learning","author":"Gu","year":"2016"},{"key":"ref10","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman","year":"2015"},{"key":"ref11","article-title":"A natural policy gradient","volume":"14","author":"Kakade","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref12","author":"Schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636681"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-021-00366-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2020.106446"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace9030163"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2021.106350"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2022.108098"},{"key":"ref19","article-title":"Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"issue":"268","key":"ref20","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2023 29th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","location":"Queenstown, New Zealand","start":{"date-parts":[[2023,11,21]]},"end":{"date-parts":[[2023,11,24]]}},"container-title":["2023 29th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10413343\/10413344\/10413400.pdf?arnumber=10413400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T15:53:16Z","timestamp":1707234796000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10413400\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,21]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/m2vip58386.2023.10413400","relation":{},"subject":[],"published":{"date-parts":[[2023,11,21]]}}}