{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:09:07Z","timestamp":1766066947412,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/iros.2018.8593619","type":"proceedings-article","created":{"date-parts":[[2019,1,23]],"date-time":"2019-01-23T21:33:30Z","timestamp":1548279210000},"page":"1569-1576","source":"Crossref","is-referenced-by-count":16,"title":["Deep Q-Learning for Dry Stacking Irregular Objects"],"prefix":"10.1109","author":[{"given":"Yifang","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seyed Mahdi","family":"Shamsi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changyou","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nils","family":"Napp","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0377-2217(95)00021-H"},{"journal-title":"Algorithms and automated material handling systems design for stacking 3d irregular stone pieces","year":"2010","author":"ko","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.4028\/www.scientific.net\/KEM.517.939"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989272"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S1526-6125(02)70129-1"},{"journal-title":"Building Stone Walls","year":"1976","author":"vivian","key":"ref15"},{"key":"ref16","volume":"217","author":"mcraven","year":"1999","journal-title":"Building Stone Walls"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"journal-title":"Cad2rl Real single-image flight without a single real image","year":"2016","author":"sadeghi","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.035"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/science.1254295"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-55146-8_8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9305-0"},{"journal-title":"Stone Walls","year":"2011","author":"cook","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08338-4_99"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460562"},{"journal-title":"Pybox2d","year":"0","key":"ref20"},{"journal-title":"MoveIt!","year":"2013","author":"sucan","key":"ref22"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/MRA.2012.2205651","article-title":"The open motion planning library","volume":"19","author":"sucan","year":"2012","journal-title":"IEEE Robotics & Automation Magazine"},{"key":"ref24","article-title":"Q-prop: Sample-efficient policy gradient with an off-policy critic","author":"gu","year":"2017","journal-title":"ICLRE"},{"key":"ref23","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"ICLRE"},{"key":"ref25","article-title":"Model-free imitation learning with policy optimization","author":"ho","year":"2016","journal-title":"ICML"}],"event":{"name":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2018,10,1]]},"location":"Madrid","end":{"date-parts":[[2018,10,5]]}},"container-title":["2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8574473\/8593358\/08593619.pdf?arnumber=8593619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T00:40:42Z","timestamp":1598229642000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8593619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iros.2018.8593619","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}