{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:49:54Z","timestamp":1767340194451,"version":"3.32.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801306","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"14026-14033","source":"Crossref","is-referenced-by-count":2,"title":["Rocket Landing Control with Random Annealing Jump Start Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yuxuan","family":"Jiang","sequence":"first","affiliation":[{"name":"Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084"}]},{"given":"Yujie","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084"}]},{"given":"Zhiqian","family":"Lan","sequence":"additional","affiliation":[{"name":"Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084"}]},{"given":"Guojian","family":"Zhan","sequence":"additional","affiliation":[{"name":"Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084"}]},{"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,College of Artificial Intelligence,Beijing,China,100084"}]},{"given":"Qi","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084"}]},{"given":"Jian","family":"Ma","sequence":"additional","affiliation":[{"name":"LandSpace Technology Corporation,Beijing,China,100176"}]},{"given":"Tianwen","family":"Yu","sequence":"additional","affiliation":[{"name":"LandSpace Technology Corporation,Beijing,China,100176"}]},{"given":"Changwu","family":"Zhang","sequence":"additional","affiliation":[{"name":"LandSpace Technology Corporation,Beijing,China,100176"}]}],"member":"263","reference":[{"article-title":"Model-based reinforcement learning for atari","volume-title":"International Conference on Learning Representations","author":"Kaiser","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3054625"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref5"},{"key":"ref6","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Haarnoja"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"article-title":"Reinforcement learning with unsupervised auxiliary tasks","volume-title":"International Conference on Learning Representations","author":"Jaderberg","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref10","first-page":"10978","article-title":"Learning near optimal policies with low inherent bellman error","volume-title":"International Conference on Machine Learning","author":"Zanette"},{"key":"ref11","article-title":"Policy finetuning: Bridging sample-efficient offline and online reinforcement learning","volume":"34","author":"Xie","year":"2021","journal-title":"Advances in neural information processing systems"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref12"},{"volume-title":"Minimum-fuel optimal trajectory for reusable first-stage rocket landing using Particle Swarm Optimization","year":"2016","author":"Anglim","key":"ref13"},{"article-title":"Awac: Accelerating online reinforcement learning with offline datasets","year":"2020","author":"Nair","key":"ref14"},{"key":"ref15","first-page":"1078","article-title":"Aw-opt: Learning robotic skills with imitation andreinforcement at scale","volume-title":"Conference on Robot Learning","author":"Lu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref17","first-page":"13399","article-title":"Pc-pg: Policy cover directed exploration for provable policy gradient learning","volume":"33","author":"Agarwal","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"34556","article-title":"Jump-start reinforcement learning","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Uchendu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"Schulman","key":"ref20"},{"issue":"1","key":"ref21","first-page":"4431","article-title":"On the theory of policy gradient methods: Optimality, approximation, and distribution shift","volume":"22","author":"Agarwal","year":"2021","journal-title":"The Journal of Machine Learning Research"},{"article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"International Conference on Learning Representations","author":"Kostrikov","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2023.100096"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3238656"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801306.pdf?arnumber=10801306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:31:19Z","timestamp":1735198279000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801306","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}