{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T15:58:40Z","timestamp":1782403120660,"version":"3.54.5"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"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":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9340929","type":"proceedings-article","created":{"date-parts":[[2021,3,15]],"date-time":"2021-03-15T14:49:56Z","timestamp":1615819796000},"page":"9705-9711","source":"Crossref","is-referenced-by-count":11,"title":["Simultaneous Planning for Item Picking and Placing by Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Tatsuya","family":"Tanaka","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toshimitsu","family":"Kaneko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masahiro","family":"Sekine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Voot","family":"Tangkaratt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masashi","family":"Sugiyama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN46459.2019.8956393"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00717"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.IR.7844"},{"key":"ref14","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref15","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"key":"ref16","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"Proceedings of The 32nd International Conference on Machine Learning"},{"key":"ref17","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in Neural Information Processing Systems 12"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref19","article-title":"A thousand ways to pack the bin – a practical approach to two-dimensional rectangle bin packing","author":"jyl\u00e4nki","year":"2010"},{"key":"ref4","article-title":"Learning to manipulate deformable objects without demonstrations","author":"wu","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref6","article-title":"The three-dimensional bin packing problem","volume":"48","author":"martello","year":"1998","journal-title":"Operations Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref8","article-title":"Ranked reward: Enabling self-play reinforcement learning for combinatorial optimization","author":"laterre","year":"2018"},{"key":"ref7","first-page":"1386","article-title":"A multi-task selected learning approach for solving 3d flexible bin packing problem","author":"duan","year":"2019","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967899"},{"key":"ref1","article-title":"A comparative review of 3d container loading algorithms","volume":"23","author":"zhao","year":"2014","journal-title":"International Transactions in Operational Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2020,10,24]]},"end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09340929.pdf?arnumber=9340929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:57:37Z","timestamp":1656453457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9340929\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9340929","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}