{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T12:55:35Z","timestamp":1730292935819,"version":"3.28.0"},"reference-count":40,"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\/robio55434.2022.10011801","type":"proceedings-article","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T18:51:38Z","timestamp":1674067898000},"page":"1439-1444","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Efficiency through Hybrid Prioritized Experience Replay in Door Environment"],"prefix":"10.1109","author":[{"given":"Haofu","family":"Qian","sequence":"first","affiliation":[{"name":"Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiqiang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjiang","family":"Ge","sequence":"additional","affiliation":[{"name":"Hangzhou Steam Turbine Co. Ltd,Hangzhou,China,310000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haolei","family":"Shi","sequence":"additional","affiliation":[{"name":"Zhoushan Institute of Calibration and Testing for Qualitative and Tech-nical Supervision,Zhoushan,China,316000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Liao","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Song","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianjun","family":"Gu","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International conference on machine learning","author":"Scott","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2988642"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"article-title":"Deep dynamics models for learning dexter-ous manipulation","volume-title":"Conference on Robot Learning","author":"Anusha","key":"ref4"},{"key":"ref5","volume":"10087","author":"Aravind","year":"2017","journal-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref8","first-page":"2684","volume":"9","author":"Zhen","year":"2019","journal-title":"A multistage game in smart grid security: A reinforcement learning solution"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490422"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3054625"},{"key":"ref11","article-title":"F1tenth: An open-source evaluation environ-ment for continuous control and reinforcement learning","volume-title":"Proceedings of Machine Learning Research","volume":"123","author":"Matthew"},{"key":"ref12","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume":"33","author":"Misha","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Towards Sample Efficient Reinforcement Learning","author":"Yang","year":"2018","journal-title":"IJCAI"},{"journal-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","year":"2019","author":"Abhishek","key":"ref14"},{"journal-title":"Accelerating reinforcement learning with learned skill priors","year":"2020","author":"Karl","key":"ref15"},{"key":"ref16","volume":"06347","author":"John","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref17","volume":"01224","author":"Ziyu","year":"2016","journal-title":"Sample efficient actor-critic with experience replay"},{"key":"ref18","volume":"05952","author":"Tom","year":"2015","journal-title":"Prioritized experience replay"},{"key":"ref19","volume":"00933","author":"Dan","year":"2018","journal-title":"Distributed prioritized experience replay"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122622"},{"article-title":"Energy-based hindsight experience pri-oritization","volume-title":"Conference on Robot Learning","author":"Rui","key":"ref21"},{"key":"ref22","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","volume-title":"International conference on machine learning","author":"Gu"},{"key":"ref23","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International Conference on Machine Learning","author":"Fujimoto"},{"journal-title":"Experience replay optimization","year":"2019","author":"Daochen","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Asia49877.2020.9276975"},{"journal-title":"PTR - PPO: Proximal Policy Optimization with Prioritized Trajectory Replay","year":"2021","author":"Xingxing","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"article-title":"Recurrent experience replay in distributed reinforcement learning","volume-title":"International conference on learning representations","author":"Steven","key":"ref28"},{"journal-title":"Curiosity-driven experience prioritization via density estimation","year":"2019","author":"Zhao","key":"ref29"},{"journal-title":"Massively parallel methods for deep reinforcement learning","year":"2015","author":"Nair","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"ref32","first-page":"3223","article-title":"Deep Q-learning from demon-strations","author":"Hester","year":"2018","journal-title":"AAAI"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref34","first-page":"1001","article-title":"Generalized prioritized sweep ing","author":"Andre","year":"1998","journal-title":"NeurIPS"},{"journal-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","year":"2017","author":"Vecer ik","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"journal-title":"Soft actor-critic algorithms and applications","year":"2018","author":"Tuomas","key":"ref37"},{"journal-title":"Mini-grid Policy Tool-kit. Policy and business frameworks for successful mini-grid roll-outs","year":"2014","author":"Michael","key":"ref38"},{"journal-title":"Doorgym: A scalable door opening environ-ment and baseline agent","year":"2019","author":"Yusuke","key":"ref39"},{"article-title":"Deterministic policy gradient algorithms","volume-title":"International conference on machine learning","author":"David","key":"ref40"}],"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\/10011801.pdf?arnumber=10011801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T02:54:30Z","timestamp":1707447270000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10011801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,5]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/robio55434.2022.10011801","relation":{},"subject":[],"published":{"date-parts":[[2022,12,5]]}}}