{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T06:10:37Z","timestamp":1769839837300,"version":"3.49.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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","award":["62125603"],"award-info":[{"award-number":["62125603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1813218"],"award-info":[{"award-number":["U1813218"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Academy of Artificial Intelligence"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/lra.2022.3222996","type":"journal-article","created":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T20:32:36Z","timestamp":1668717156000},"page":"81-88","source":"Crossref","is-referenced-by-count":24,"title":["Planning Irregular Object Packing via Hierarchical Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4206-614X","authenticated-orcid":false,"given":"Sichao","family":"Huang","sequence":"first","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology (BNRist), the Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9225-8495","authenticated-orcid":false,"given":"Ziwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology (BNRist), the Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7701-234X","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology (BNRist), the Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology (BNRist), the Department of Automation, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417796"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/267"},{"key":"ref32","first-page":"28182","article-title":"Towards mental time travel: A hierarchical memory for reinforcement learning agents","volume":"34","author":"lampinen","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3059912"},{"key":"ref30","article-title":"Landmark-guided subgoal generation in hierarchical reinforcement learning","volume":"34","author":"kim","year":"0","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref36","first-page":"3915","article-title":"SGM: Sequence generation model for multi-label classification","author":"yang","year":"0","journal-title":"Proc 27th Int Conf Comput Linguistics"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3071062"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16580"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-018-1132-7"},{"key":"ref40","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"Proc Int Conf Med Image Comput Comput - Assist Intervention"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2022.108122"},{"key":"ref12","first-page":"1","article-title":"Attend2Pack: Bin packing through deep reinforcement learning with attention","author":"zhang","year":"0","journal-title":"Proc Int Conf Mach Learn Workshop"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105400"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2018.03.029"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.105565"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-58891-4_84"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.15.3.267.16080"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2016.06.003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1061\/9780784482438.026"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2020.101234"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2988262"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30198-1_45"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16155"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2017.2669335"},{"key":"ref5","article-title":"Solving a new 3D bin packing problem with deep reinforcement learning method","author":"hu","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.06.050"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF02187720"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340929"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105245"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794049"},{"key":"ref20","first-page":"3700","article-title":"Packit: A virtual environment for geometric planning","author":"goyal","year":"0","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref22","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref21","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3129136"},{"key":"ref24","first-page":"556","article-title":"Intra-option learning about temporally abstract actions","author":"sutton","year":"0","journal-title":"Proc 15th Int Conf Mach Learn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2015.2448951"},{"key":"ref23","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"0","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref44","first-page":"1","article-title":"GE-Grasp: Efficient target-oriented grasping in dense clutter","author":"liu","year":"0","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00433-9"},{"key":"ref43","first-page":"1","article-title":"Smart explorer: Recognizing objects in dense clutter via interactive exploration","author":"wu","year":"0","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref25","first-page":"1","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"florensa","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9963768\/09954127.pdf?arnumber=9954127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:23:34Z","timestamp":1670873014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9954127\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":44,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3222996","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}