{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:19:14Z","timestamp":1781086754689,"version":"3.54.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016311","name":"Arm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561439","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"4776-4782","source":"Crossref","is-referenced-by-count":15,"title":["Causal Reasoning in Simulation for Structure and Transfer Learning of Robot Manipulation Policies"],"prefix":"10.1109","author":[{"given":"Tabitha E.","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialiang Alan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amrita S.","family":"Sawhney","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siddharth","family":"Girdhar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oliver","family":"Kroemer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Exact Solutions to the Nonlinear Dynamics of Learning in Deep Linear Neural Networks","author":"saxe","year":"2014","journal-title":"Int’l Conf on Learning Representations (ICLR2017)"},{"key":"ref32","article-title":"The Expressive Power of Neural Networks: A View from the Width","author":"lu","year":"2017","journal-title":"Conf on Neural Information Processing Systems (NeurIPS)"},{"key":"ref31","article-title":"Actor-Critic Algorithms","author":"konda","year":"2000","journal-title":"Conf on Neural Information Processing Systems (NeurIPS)"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative Entropy Policy Search","author":"peters","year":"2010","journal-title":"AAAI Conf on Artificial Intelligence"},{"key":"ref36","article-title":"Progressive Neural Networks","author":"rusu","year":"2016","journal-title":"arXiv preprint arXiv 1606 04671"},{"key":"ref35","article-title":"Stable Baselines","author":"hill","year":"2018"},{"key":"ref34","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref10","article-title":"Causal Confusion in Imitation Learning","author":"de haan","year":"2019","journal-title":"Conf on Neural Information Processing Systems (NeurIPS)"},{"key":"ref11","article-title":"Causal Discovery in Physical Systems from Videos","author":"li","year":"2020","journal-title":"Conf on Neural Information Processing Systems (NeurIPS)"},{"key":"ref12","article-title":"Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning","author":"sontakke","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref14","article-title":"CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning","author":"ahmed","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461196"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.048"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5202-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553442"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390251"},{"key":"ref28","article-title":"Recurrent World Models Facilitate Policy Evolution","author":"ha","year":"2018","journal-title":"Conf on Neural Information Processing Systems (NeurIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1306572110"},{"key":"ref3","article-title":"A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms","author":"kroemer","year":"2019","journal-title":"arXiv preprint arXiv 1907 09977"},{"key":"ref6","article-title":"GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning","author":"liang","year":"2018","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref8","article-title":"Causality for Machine Learning","author":"sch\u00f6lkopf","year":"2019","journal-title":"arXiv preprint arXiv 1911 12945"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx137"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/186"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967695"},{"key":"ref24","article-title":"Deep Reinforcement Learning in Parameterized Action Space","author":"hausknecht","year":"2016","journal-title":"Int’l Conf on Learning Representations (ICLR2017)"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10226","article-title":"Reinforcement Learning with Parameterized Actions","author":"masson","year":"2016","journal-title":"AAAI Conf on Artificial Intelligence"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A Survey on Policy Search for Robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/316"}],"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\/09561439.pdf?arnumber=9561439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:55:34Z","timestamp":1673564134000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561439","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}