{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:36:20Z","timestamp":1781109380046,"version":"3.54.1"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"InnoHK of the Government of the Hong Kong Special Administrative Region via the Hong Kong Centre for Logistics Robotics"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/lra.2024.3440731","type":"journal-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T18:44:04Z","timestamp":1723142644000},"page":"9303-9310","source":"Crossref","is-referenced-by-count":13,"title":["Efficient Reinforcement Learning of Task Planners for Robotic Palletization Through Iterative Action Masking Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3248-4153","authenticated-orcid":false,"given":"Zheng","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8473-5378","authenticated-orcid":false,"given":"Yichuan","family":"Li","sequence":"additional","affiliation":[{"name":"T Stone Robotics Institute, Department of Mechanical and Automation Engineering, Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1474-1200","authenticated-orcid":false,"given":"Wei","family":"Zhan","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3767-5517","authenticated-orcid":false,"given":"Changliu","family":"Liu","sequence":"additional","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3625-6679","authenticated-orcid":false,"given":"Yun-Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"T Stone Robotics Institute, Department of Mechanical and Automation Engineering, Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0206-6639","authenticated-orcid":false,"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3024291"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30198-1_45"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55792-2_10"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794049"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16155"},{"key":"ref6","article-title":"Learning efficient online 3D bin packing on packing configuration trees","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3348-6"},{"key":"ref8","article-title":"Starcraft II: A new challenge for reinforcement learning","author":"Vinyals","year":"2017"},{"key":"ref9","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref11","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","author":"Chen","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref13","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Ross","year":"2011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/opre.48.2.256.12386"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.15.3.267.16080"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2007.06.063"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2012.07.036"},{"issue":"6","key":"ref18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3414685.3417764","article-title":"TAP-Net: Transport-and-pack using reinforcement learning","volume":"39","author":"Hu","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"ref19","article-title":"Attend2pack: Bin packing through deep reinforcement learning with attention","author":"Zhang","year":"2021"},{"key":"ref20","article-title":"Deep reinforcement learning in large discrete action spaces","author":"Dulac-Arnold","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref23","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref24","first-page":"1634","article-title":"Smooth exploration for robotic reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Raffin","year":"2022"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10683798\/10631682.pdf?arnumber=10631682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:34:48Z","timestamp":1734982488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10631682\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":24,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3440731","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}