{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T19:47:01Z","timestamp":1773776821130,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197020","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T17:25:46Z","timestamp":1600190746000},"page":"2167-2173","source":"Crossref","is-referenced-by-count":19,"title":["Scalable Multi-Task Imitation Learning with Autonomous Improvement"],"prefix":"10.1109","author":[{"given":"Avi","family":"Singh","sequence":"first","affiliation":[]},{"given":"Eric","family":"Jang","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Irpan","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Kappler","sequence":"additional","affiliation":[]},{"given":"Murtaza","family":"Dalal","sequence":"additional","affiliation":[]},{"given":"Sergey","family":"Levinev","sequence":"additional","affiliation":[]},{"given":"Mohi","family":"Khansari","sequence":"additional","affiliation":[]},{"given":"Chelsea","family":"Finn","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"coumans","year":"2016","journal-title":"Github Repository"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref33","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref32","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref31","article-title":"Maximum entropy deep inverse reinforcement learning","volume":"abs 1507 4888","author":"wulfmeier","year":"2015","journal-title":"Neural Information Processing Systems Conference Deep Reinforcement Learning Workshop"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1145\/1143844.1143936","article-title":"Maximum margin planning","author":"ratli","year":"2006","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref36","article-title":"Rl2: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2016"},{"key":"ref35","article-title":"Learning an embedding space for transferable robot skills","author":"hausman","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref34","article-title":"Vision-based multi-task manipulation for inexpensive robots using end-to-end learning from demonstration","volume":"abs 1707 2920","author":"rahmatizadeh","year":"2017","journal-title":"CoRR"},{"key":"ref10","article-title":"Deep reinforcement learning doesn’t work yet","author":"irpan","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460609"},{"key":"ref11","article-title":"Challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2019"},{"key":"ref12","first-page":"3309","article-title":"Deeply aggrevated: Differentiable imitation learning for sequential prediction","volume":"70","author":"sun","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref13","first-page":"661","article-title":"E cient reductions for imitation learning","author":"ross","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907421"},{"key":"ref15","article-title":"One-shot imitation learning","author":"duan","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref16","article-title":"One-shot visual imitation learning via meta-learning","author":"finn","year":"2017","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.002"},{"key":"ref18","article-title":"Task-embedded control networks for few-shot imitation learning","author":"james","year":"2018"},{"key":"ref19","article-title":"Neural task graphs: Generalizing to unseen tasks from a single video demonstration","author":"huang","year":"2018"},{"key":"ref28","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"International Conference on Machine Leanring (ICML)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_18"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2002.1258"},{"key":"ref3","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref6","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref5","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"0","journal-title":"Proc 2nd Conf Robot Lear"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.073"},{"key":"ref7","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"Tech Rep"},{"key":"ref2","article-title":"Deep imitation learning for complex manipulation tasks from virtual reality teleoperation","author":"zhang","year":"2017"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11694","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref1","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref20","article-title":"Watch, try, learn: Meta-learning from demonstrations and reward","author":"zhou","year":"0"},{"key":"ref22","article-title":"Learning to achieve goals","author":"kaelbling","year":"1993","journal-title":"Proceedings of the 13th International Joint Conference on Artificial Intelligence 1993"},{"key":"ref21","article-title":"One-shot high-fidelity imitation: Training large-scale deep nets with rl","author":"paine","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.020"},{"key":"ref23","first-page":"5055","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref26","article-title":"One-shot imitation learning","author":"duan","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref25","article-title":"Hindsight policy gradients","author":"rauber","year":"2017"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197020.pdf?arnumber=9197020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T09:02:32Z","timestamp":1668762152000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197020","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}