{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T17:40:05Z","timestamp":1769794805900,"version":"3.49.0"},"reference-count":35,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,8]]},"DOI":"10.1109\/coase.2016.7743488","type":"proceedings-article","created":{"date-parts":[[2016,11,17]],"date-time":"2016-11-17T16:35:22Z","timestamp":1479400522000},"page":"827-834","source":"Crossref","is-referenced-by-count":50,"title":["Robot grasping in clutter: Using a hierarchy of supervisors for learning from demonstrations"],"prefix":"10.1109","author":[{"given":"Michael","family":"Laskey","sequence":"first","affiliation":[]},{"given":"Jonathan","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Caleb","family":"Chuck","sequence":"additional","affiliation":[]},{"given":"David","family":"Gealy","sequence":"additional","affiliation":[]},{"given":"Wesley","family":"Hsieh","sequence":"additional","affiliation":[]},{"given":"Florian T.","family":"Pokorny","sequence":"additional","affiliation":[]},{"given":"Anca D.","family":"Dragan","sequence":"additional","affiliation":[]},{"given":"Ken","family":"Goldberg","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363986"},{"key":"ref31","author":"scholkopf","year":"2002","journal-title":"Learning With Kernels Support Vector Machines Regularization Optimization and Beyond"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/70.294207"},{"key":"ref35","first-page":"599","article-title":"Path planning among movable obstacles: a probabilistically complete approach","author":"van","year":"2009","journal-title":"Algorithmic Foundation of Robotics VIII"},{"key":"ref34","first-page":"2074","article-title":"Superhuman performance of surgical tasks by robots using iterative learning from human-guided demonstrations","author":"van","year":"2010","journal-title":"IEEE ICRA 2010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2012.VIII.008"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.009"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630702"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363692"},{"key":"ref14","first-page":"3338","article-title":"Deep learning for real-time atari game play using offline monte-carlo tree search planning","author":"guo","year":"2014","journal-title":"NIPS"},{"key":"ref15","article-title":"Active imitation learning via state queries","author":"judah","year":"2011","journal-title":"Proceedings of the ICML Workshop on Combining Learning Strategies to Reduce Label Cost"},{"key":"ref16","article-title":"How can robots succeed in unstructured environments","author":"katz","year":"2008","journal-title":"In Workshop on Robot Manipulation Intelligence in Human Environments at Robotics Science and Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2013.IX.038"},{"key":"ref18","article-title":"Nonprehen-sile whole arm rearrangement planning on physics manifolds","author":"king","year":"0","journal-title":"IEEE ICRA 2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139625"},{"key":"ref28","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2010","journal-title":"arXiv preprint arXiv 1011 0686"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref27","first-page":"661","article-title":"Efficient reductions for imitation learning","author":"ross","year":"2010","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4651222"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844081"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630809"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1613\/jair.2584","article-title":"Interactive policy learning through confidence-based autonomy","volume":"34","author":"chernova","year":"2009","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref7","author":"bradski","year":"2000","journal-title":"Dr Dobb's Journal of Software Tools"},{"key":"ref2","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","volume":"19","author":"abbeel","year":"2007","journal-title":"NIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094737"},{"key":"ref1","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015","journal-title":"software available from tensorflow org"},{"key":"ref20","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157691"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487167"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/027836498600500303"},{"key":"ref23","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2015","journal-title":"arXiv preprint arXiv 1504 00702"},{"key":"ref26","article-title":"Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours","author":"pinto","year":"2015","journal-title":"arXiv preprint arXiv 1509 06825"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630892"}],"event":{"name":"2016 IEEE International Conference on Automation Science and Engineering (CASE)","location":"Fort Worth, TX, USA","start":{"date-parts":[[2016,8,21]]},"end":{"date-parts":[[2016,8,25]]}},"container-title":["2016 IEEE International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7738291\/7743369\/07743488.pdf?arnumber=7743488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,15]],"date-time":"2019-09-15T14:35:39Z","timestamp":1568558139000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7743488\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/coase.2016.7743488","relation":{},"subject":[],"published":{"date-parts":[[2016,8]]}}}