{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:10:19Z","timestamp":1730297419199,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/smc53992.2023.10393949","type":"proceedings-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T18:32:04Z","timestamp":1706553124000},"page":"114-119","source":"Crossref","is-referenced-by-count":0,"title":["Guided Reward Design in Continuous Reinforcement Learning for Quantum Control"],"prefix":"10.1109","author":[{"given":"Shumin","family":"Zhou","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Department of Automation,Hefei,China,230027"}]},{"given":"Hailan","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Engineering and Information Technology, University of New South Wales,Canberra,ACT,Australia,2600"}]},{"given":"Sen","family":"Kuang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Department of Automation,Hefei,China,230027"}]},{"given":"Daoyi","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Engineering and Information Technology, University of New South Wales,Canberra,ACT,Australia,2600"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2921424"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2022.04.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20245-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/acab24"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1140\/epjqt\/s40507-022-00138-x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.130.043604"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110201"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2610979"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2020.3018500"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.99.042327"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2009.0508"},{"key":"ref12","first-page":"63","article-title":"Model uncertainty and robust control","author":"Astrom","year":"2000","journal-title":"Lecture Notes on Iterative Identification and Control Design"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmr.2004.11.004"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SMC42975.2020.9282921"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2283574"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SMC52423.2021.9658732"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.031086"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41534-019-0141-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3153502"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3243187"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"journal-title":"Deep reinforcement learning for autonomous driving","year":"2018","author":"Wang","key":"ref24"},{"key":"ref25","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI51109.2021.00091"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref28","article-title":"A study on overfitting in deep reinforcement learning","author":"Zhang","year":"2018","journal-title":"ar Xiv preprint"},{"key":"ref29","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"Ng","year":"1999","journal-title":"ICML"},{"key":"ref30","first-page":"4870","article-title":"Reward-free exploration for reinforcement learning","volume-title":"International Conference on Machine Learning. PMLR","author":"Jin","year":"2020"},{"key":"ref31","first-page":"1","article-title":"Reinforcement learning for humanoid robotics","volume-title":"Proceedings of the third IEEE-RAS International Conference on Humanoid Robots","author":"Peters","year":"2003"},{"key":"ref32","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"Ng","year":"2000","journal-title":"ICML"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1017\/9781316995433"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/nphys2170"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936863"},{"key":"ref36","article-title":"Hind-sight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.54.2084"},{"journal-title":"Sample efficient actor-critic with experience replay","year":"2016","author":"Wang","key":"ref38"},{"key":"ref39","article-title":"Recurrent experience replay in distributed reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Kapturowski","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/s41534-019-0201-8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.78.042307"}],"event":{"name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2023,10,1]]},"location":"Honolulu, Oahu, HI, USA","end":{"date-parts":[[2023,10,4]]}},"container-title":["2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10391856\/10393862\/10393949.pdf?arnumber=10393949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:56:46Z","timestamp":1706792206000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10393949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/smc53992.2023.10393949","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}