{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T05:17:04Z","timestamp":1735276624748,"version":"3.32.0"},"reference-count":43,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802526","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"8039-8046","source":"Crossref","is-referenced-by-count":0,"title":["Mastering Scene Rearrangement with Expert-Assisted Curriculum Learning and Adaptive Trade-Off Tree-Search"],"prefix":"10.1109","author":[{"given":"Zan","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Thinking fast and slow with deep learning and tree search","author":"Anthony","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"article-title":"Rearrangement: A challenge for embodied ai","year":"2020","author":"Batra","key":"ref3"},{"article-title":"Fast pol-icy learning through imitation and reinforcement","year":"2018","author":"Cheng","key":"ref4"},{"article-title":"Off-policy actor-critic","volume-title":"International Conference on Machine Learning (ICML)","author":"Degris","key":"ref5"},{"article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","year":"2018","author":"Ebert","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"article-title":"D4rl: Datasets for deep data-driven reinforcement learning","year":"2020","author":"Fu","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812367"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342164"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01437"},{"key":"ref12","article-title":"Deep learning for real-time atari game play using offline montecarlo tree search planning","author":"Guo","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"article-title":"Learning manipulation states and actions for efficient non-prehensile rearrangement planning","year":"2019","author":"Haustein","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417796"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3123373"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3222996"},{"article-title":"Way off-policy batch deep reinforcement learning of implicit human preferences in dialog","year":"2019","author":"Jaques","key":"ref17"},{"article-title":"Doubly robust off-policy value evaluation for reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Jiang","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487583"},{"article-title":"Bandit based montecarlo planning","volume-title":"European Conference on Machine Learning (ECML)","author":"Kocsis","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353743"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2980984"},{"issue":"181","key":"ref23","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","article-title":"Atiss: Autoregressive transformers for indoor scene synthesis","author":"Paschalidou","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"volume-title":"Markov decision processes: discrete stochastic dynamic programming.","year":"2014","author":"Puterman","key":"ref25"},{"article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"International Conference on Artificial Intelligence and Statistics (ICAIS)","author":"Ross","key":"ref26"},{"article-title":"Trust region policy optimization","volume-title":"International Conference on Machine Learning (ICML)","author":"Schulman","key":"ref27"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref28"},{"article-title":"Approximately optimal approximate reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Sham","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967548"},{"key":"ref32","article-title":"Dual policy iteration","author":"Sun","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"article-title":"Data-efficient off-policy policy evaluation for reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Thomas","key":"ref33"},{"article-title":"Deep reinforcement learning and the deadly triad","year":"2018","author":"Van Hasselt","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811848"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417788"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00586"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3005680"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964981"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.06.007"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610792"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3381866"}],"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\/10802526.pdf?arnumber=10802526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:23:09Z","timestamp":1735197789000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802526\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802526","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}