{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T14:12:09Z","timestamp":1762956729859,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"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":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636280","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"2398-2405","source":"Crossref","is-referenced-by-count":7,"title":["Learning to Design and Construct Bridge without Blueprint"],"prefix":"10.1109","author":[{"given":"Yunfei","family":"Li","sequence":"first","affiliation":[]},{"given":"Tao","family":"Kong","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yifeng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"year":"2020","author":"hsu","article-title":"Revisiting design choices in proximal policy optimization","key":"ref33"},{"key":"ref32","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"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/IROS.2012.6386109"},{"year":"0","author":"li","article-title":"Solving compositional reinforcement learning problems via task reduction","key":"ref30"},{"year":"2018","author":"zhou","article-title":"Open3D: A modern library for 3D data processing","key":"ref35"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/IROS45743.2020.9341428"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/978-3-319-16595-0_11"},{"key":"ref12","first-page":"1930","article-title":"Logic-geometric programming: An optimization-based approach to combined task and motion planning","author":"toussaint","year":"2015","journal-title":"IJCAI"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1016\/0004-3702(74)90008-3"},{"key":"ref14","article-title":"Combined task and motion planning for mobile manipulation","volume":"20","author":"wolfe","year":"2010","journal-title":"Proceedings of the International Conference on Automated Planning and Scheduling"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICRA.2019.8793506"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICRA40945.2020.9196733"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1111\/cgf.12580"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1145\/2766895"},{"year":"2016","author":"battaglia","article-title":"Interaction networks for learning about objects, relations and physics","key":"ref19"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICRA40945.2020.9197468"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"ref27","article-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","author":"sukhbaatar","year":"2018","journal-title":"International Conference on Learning Representations"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICRA.2014.6906922"},{"year":"2020","author":"zhao","article-title":"Online 3d bin packing with constrained deep reinforcement learning","key":"ref6"},{"year":"2020","author":"zhu","article-title":"Hierarchical planning for long-horizon manipulation with geometric and symbolic scene graphs","key":"ref5"},{"key":"ref29","first-page":"3681","article-title":"Mcp: Learning composable hierarchical control with multiplicative compositional policies","author":"peng","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Phasic policy gradient","author":"cobbe","year":"2020","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/LRA.2020.3043168"},{"year":"1998","author":"mcdermott","article-title":"Pddl-the planning domain definition language","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICRA.2011.5980391"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICRA.2013.6630673"},{"year":"0","author":"janner","article-title":"Reasoning about physical interactions with object-centric models","key":"ref20"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1145\/1553374.1553380"},{"year":"2020","author":"mu","article-title":"Refactoring policy for compositional generalizability using self-supervised object proposals","key":"ref21"},{"key":"ref24","first-page":"1162","article-title":"Active domain randomization","author":"mehta","year":"2020","journal-title":"Conference on Robot Learning"},{"year":"2019","author":"akkaya","article-title":"Solving rubik’s cube with a robot hand","key":"ref23"},{"key":"ref26","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref25","first-page":"1515","article-title":"Automatic goal generation for reinforcement learning agents","author":"florensa","year":"2018","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2021,9,27]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636280.pdf?arnumber=9636280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:45Z","timestamp":1652201685000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636280\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636280","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}