{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,8]],"date-time":"2025-03-08T08:10:22Z","timestamp":1741421422895,"version":"3.38.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92248304"],"award-info":[{"award-number":["92248304"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,10]]},"DOI":"10.1109\/robio64047.2024.10907722","type":"proceedings-article","created":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:33:40Z","timestamp":1741372420000},"page":"1862-1867","source":"Crossref","is-referenced-by-count":0,"title":["Novelty-based Sample Reuse for Continuous Robotics Control"],"prefix":"10.1109","author":[{"given":"Ke","family":"Duan","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Houde","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","author":"Achiam","year":"2017","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Hindsight experience replay","author":"Andrychowicz","year":"2017","journal-title":"arXiv"},{"key":"ref3","first-page":"263","article-title":"Minimax regret bounds for rein-forcement learning","volume-title":"International conference on machine learning","author":"Azar","year":"2017"},{"key":"ref4","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"Bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"Exploration by random network distillation","author":"Burda","year":"2018","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"Chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"617","article-title":"Model-based reinforcement learning via meta-policy optimization","volume-title":"Conference on Robot Learning","author":"Clavera","year":"2018"},{"key":"ref8","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"International conference on machine learning","author":"Duan","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref10","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn","year":"2017"},{"journal-title":"Addressing function approximation error in actor-critic methods","year":"2018","author":"Fujimoto","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref13","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":"ref14","article-title":"When to trust your model: Model-based policy optimization","volume":"32","author":"Janner","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Model-based reinforcement learning for atari","author":"Kaiser","year":"2019","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"journal-title":"Controlling overestimation bias with truncated mixture of continuous distributional quantile critics","year":"2020","author":"Kuznetsov","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref20","article-title":"Continuous control with deep reinforcement learning","volume":"02971","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5955"},{"key":"ref23","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"journal-title":"The primacy bias in deep reinforcement learning","year":"2022","author":"Nikishin","key":"ref25"},{"key":"ref26","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"International conference on machine learning","author":"Ostrovski","year":"2017"},{"key":"ref27","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","author":"Parisotto","year":"2015","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref29","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018","journal-title":"arXiv preprint"},{"key":"ref30","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"International conference on machine learning","author":"Rakelly","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834710"},{"key":"ref32","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Proxi-mal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref34"},{"key":"ref35","volume-title":"Introduction to reinforcement learning","volume":"135","author":"Sutton","year":"1998"},{"key":"ref36","article-title":"Exploration and anti-exploration with distributional random network distillation","volume":"09750","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"14129","article-title":"Mopo: Model-based offline policy optimization","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"}],"event":{"name":"2024 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2024,12,10]]},"location":"Bangkok, Thailand","end":{"date-parts":[[2024,12,14]]}},"container-title":["2024 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10906779\/10907273\/10907722.pdf?arnumber=10907722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,8]],"date-time":"2025-03-08T07:55:30Z","timestamp":1741420530000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10907722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/robio64047.2024.10907722","relation":{},"subject":[],"published":{"date-parts":[[2024,12,10]]}}}