{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T08:20:43Z","timestamp":1774686043905,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811624","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"7469-7476","source":"Crossref","is-referenced-by-count":3,"title":["Learning Design and Construction with Varying-Sized Materials via Prioritized Memory Resets"],"prefix":"10.1109","author":[{"given":"Yunfei","family":"Li","sequence":"first","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University,Beijing,China"}]},{"given":"Tao","family":"Kong","sequence":"additional","affiliation":[{"name":"ByteDance AI Lab,Beijing,China"}]},{"given":"Lei","family":"Li","sequence":"additional","affiliation":[{"name":"University of California,Santa Barbara"}]},{"given":"Yi","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University,Beijing,China"}]}],"member":"263","reference":[{"key":"ref39","author":"coumans","year":"2016","journal-title":"Pybullet a python module for physics simulation for games robotics and machine learning"},{"key":"ref38","article-title":"Self-supervised policy adaptation during deployment","author":"hansen","year":"2021","journal-title":"9th International Conference on Learning Representations ICLR 2021"},{"key":"ref33","article-title":"Exploration by random network distillation","author":"burda","year":"2019","journal-title":"7th International Conference on Learning Representations ICLR 2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21236\/ADA440280"},{"key":"ref31","article-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","author":"sukhbaatar","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref30","article-title":"Automatic curriculum learning through value disagreement","volume":"33","author":"zhang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref34","article-title":"Large-scale study of curiosity-driven learning","author":"burda","year":"2019","journal-title":"ICLRE"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561315"},{"key":"ref40","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems 30 Annual Conference on Neural Information Processing Systems 2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094992"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793506"},{"key":"ref13","article-title":"Hierarchical planning for long-horizon manipulation with geometric and symbolic scene graphs","author":"zhu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636280"},{"key":"ref15","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref16","first-page":"1515","article-title":"Automatic goal generation for reinforcement learning agents","author":"florensa","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630673"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341428"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196733"},{"key":"ref28","article-title":"Option discovery using deep skill chaining","author":"bagaria","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref4","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"yu","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref27","article-title":"Near-optimal representation learning for hierarchical reinforcement learning","author":"nachum","year":"2019","journal-title":"7th International Conference on Learning Representations ICLR 2019"},{"key":"ref3","article-title":"Solving rubik's cube with a robot hand","author":"akkaya","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref29","article-title":"Learning and transfer of modulated locomotor controllers","volume":"abs 1610 5182","author":"heess","year":"2016","journal-title":"CoRR"},{"key":"ref5","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","author":"plappert","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197468"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref9","first-page":"603","article-title":"HRL4IN: hierarchical reinforcement learning for interactive navigation with mobile manipulators","volume":"100","author":"li","year":"0","journal-title":"3rd Annual Conference on Robot Learning CoRL 2019 Osaka Japan October 30 – November 1 2019 Proceedings ser Proceedings of Machine Learning Research"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12580"},{"key":"ref21","article-title":"Rearrangement: A challenge for embodied AI","volume":"abs 2011 1975","author":"batra","year":"2020","journal-title":"CoRR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844730"},{"key":"ref24","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume":"29","author":"kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref41","article-title":"Phasic policy gradient","volume":"abs 2009 4416","author":"cobbe","year":"2020","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2766895"},{"key":"ref44","article-title":"The OpenCV Library","author":"bradski","year":"2000","journal-title":"Dr Dobb's Journal of Software Tools"},{"key":"ref26","first-page":"3307","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"Advances in Neural Information Processing Systems 31 Annual Conference on Neural Information Processing Systems 2018 NeurIPS 2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.01.005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811624.pdf?arnumber=9811624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:05:59Z","timestamp":1667516759000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811624\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811624","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}