{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T20:44:41Z","timestamp":1754599481628,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610992","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"9502-9508","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Level Progressive Reinforcement Learning for Control Policy in Physical Simulations"],"prefix":"10.1109","author":[{"given":"Kefei","family":"Wu","sequence":"first","affiliation":[{"name":"ShanghaiTech University"}]},{"given":"Xuming","family":"He","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}]},{"given":"Xiaopei","family":"Liu","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}]}],"member":"263","reference":[{"year":"2016","author":"Coumans","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","key":"ref1"},{"key":"ref2","first-page":"13","article-title":"SOFA - an Open Source Framework for Medical Simulation","volume":"125","author":"Allard","year":"2007","journal-title":"MMVR 15-Medicine Meets Virtual Reality"},{"key":"ref3","first-page":"1","article-title":"OpenFOAM: A C++ library for complex physics simulations","volume-title":"International workshop on coupled methods in numerical dynamics","volume":"1000","author":"Jasak"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1145\/3355089.3356497"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TRO.2022.3181014"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1145\/3386569.3392400"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TVCG.2021.3059753"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1145\/3554731"},{"year":"2008","author":"M\u00fcller","article-title":"Hierarchical position based dynamics","key":"ref9"},{"key":"ref10","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","author":"Haarnoja","article-title":"Soft Actor-Critic Algorithms and Applications","key":"ref11"},{"year":"2016","author":"Brockman","article-title":"OpenAI Gym","key":"ref12"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1007\/978-3-319-67361-5_40"},{"year":"2021","author":"Makoviychuk","article-title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/LRA.2018.2795643"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/TMECH.2012.2226049"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.2514\/6.2020-1721"},{"issue":"2","key":"ref18","first-page":"267","article-title":"Validation of hyperflow in subsonic and transonic flow","volume":"34","author":"He","year":"2016","journal-title":"Acta Aerodynamica Sinica"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICRA.2018.8463189"},{"year":"2020","author":"Julian","article-title":"Never stop learning: The effectiveness of fine-tuning in robotic reinforcement learning","key":"ref20"},{"year":"2021","author":"Campos","article-title":"Beyond fine-tuning: Transferring behavior in reinforcement learning","key":"ref21"},{"key":"ref22","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Mnih"},{"year":"2017","author":"Gruslys","article-title":"The reactor: A fast and sample-efficient actor-critic agent for reinforcement learning","key":"ref23"},{"key":"ref24","first-page":"1407","article-title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","volume-title":"International conference on machine learning","author":"Espeholt"},{"year":"2018","author":"Horgan","article-title":"DISTRIBUTED PRIORITIZED EXPERIENCE REPLAY","key":"ref25"},{"year":"2016","author":"Rusu","article-title":"Progressive Neural Networks","key":"ref26"},{"key":"ref27","first-page":"270","article-title":"GPU-accelerated robotic simulation for distributed reinforcement learning","volume-title":"Conference on Robot Learning","author":"Liang"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1063\/1.5116415"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref29"},{"volume-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","year":"2010","author":"Ziebart","key":"ref30"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1126\/scirobotics.abc5986"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1038\/323533a0"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/ICRA46639.2022.9812066"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610992.pdf?arnumber=10610992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:22:17Z","timestamp":1723267337000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610992","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}