{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T18:21:05Z","timestamp":1773858065062,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9560986","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"6343-6349","source":"Crossref","is-referenced-by-count":59,"title":["IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks"],"prefix":"10.1109","author":[{"given":"Youngwoon","family":"Lee","sequence":"first","affiliation":[{"name":"University of Southern California,Department of Computer Science,Los Angeles,CA"}]},{"given":"Edward S.","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,Department of Computer and Information Science,Philadelphia,PA"}]},{"given":"Joseph J.","family":"Lim","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Computer Science,Los Angeles,CA"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2469","article-title":"Policy optimization with demonstrations","volume":"80","author":"kang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref38","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref33","article-title":"Decoupling representation learning from reinforcement learning","author":"stooke","year":"2020"},{"key":"ref32","article-title":"Reinforcement learning with augmented data","author":"laskin","year":"2020"},{"key":"ref31","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"yarats","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref30","article-title":"Accelerating reinforcement learning with learned skill priors","author":"pertsch","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref36","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref35","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref12","article-title":"Starcraft ii: A new challenge for reinforcement learning","author":"vinyals","year":"2017"},{"key":"ref13","article-title":"Airsim: High-fidelity visual and physical simulation for autonomous vehicles","author":"shah","year":"2017","journal-title":"Field and Service Robotics"},{"key":"ref14","first-page":"1","article-title":"CARLA: An open urban driving simulator","author":"dosovitskiy","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref15","article-title":"Ai2-thor: An interactive 3d environment for visual ai","author":"kolve","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref19","article-title":"Composing complex skills by learning transition policies","author":"lee","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref28","first-page":"1087","article-title":"One-shot imitation learning","author":"duan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"zhu","year":"2020"},{"key":"ref27","article-title":"Pyrobolearn: A python framework for robot learning practitioners","author":"delhaisse","year":"2019","journal-title":"Conference on Robot Learning"},{"key":"ref3","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"yu","year":"2019","journal-title":"Conference on Robot Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2013.IX.048"},{"key":"ref29","article-title":"Relay policy learning: Solving long horizon tasks via imitation and reinforcement learning","author":"gupta","year":"2019","journal-title":"Conference on Robot Learning"},{"key":"ref5","article-title":"dm control: Software and tasks for continuous control","author":"tassa","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat6385"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630673"},{"key":"ref2","article-title":"Rlbench: The robot learning benchmark & learning environment","author":"james","year":"2019"},{"key":"ref9","article-title":"Unity: A general platform for intelligent agents","author":"juliani","year":"2018"},{"key":"ref1","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref20","article-title":"Recogym: A reinforcement learning environment for the problem of product recommendation in online advertising","author":"rohde","year":"2018"},{"key":"ref22","article-title":"Learning dexterous in-hand manipulation","author":"andrychowicz","year":"2018"},{"key":"ref21","article-title":"To follow or not to follow: Selective imitation learning from observations","author":"lee","year":"2019","journal-title":"Conference on Robot Learning"},{"key":"ref24","article-title":"Doorgym: A scalable door opening environment and baseline agent","author":"urakami","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref26","article-title":"Motion planner augmented reinforcement learning for obstructed environments","author":"yamada","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09560986.pdf?arnumber=9560986","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:21:21Z","timestamp":1659482481000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9560986\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9560986","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}