{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:40:13Z","timestamp":1735198813142,"version":"3.32.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802173","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"11155-11162","source":"Crossref","is-referenced-by-count":0,"title":["Working Backwards: Learning to Place by Picking"],"prefix":"10.1109","author":[{"given":"Oliver","family":"Limoyo","sequence":"first","affiliation":[{"name":"Samsung AI Centre,Montréal,Canada,H3A 3G4"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhisek","family":"Konar","sequence":"additional","affiliation":[{"name":"Samsung AI Centre,Montréal,Canada,H3A 3G4"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Ablett","sequence":"additional","affiliation":[{"name":"Samsung AI Centre,Montréal,Canada,H3A 3G4"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Kelly","sequence":"additional","affiliation":[{"name":"STARS Laboratory, University of Toronto Institute for Aerospace Studies,Toronto,Canada,M5S 1A4"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francois R.","family":"Hogan","sequence":"additional","affiliation":[{"name":"Samsung AI Centre,Montréal,Canada,H3A 3G4"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory","family":"Dudek","sequence":"additional","affiliation":[{"name":"Samsung AI Centre,Montréal,Canada,H3A 3G4"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636440"},{"key":"ref2","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Conf. Robot Learning (CORL)","author":"Florence"},{"article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","year":"2023","author":"Blattmann","key":"ref3"},{"journal-title":"tech. rep","article-title":"GPT-4 Technical Report","year":"2023","key":"ref4"},{"key":"ref5","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conf. Robot Learning (CORL)","author":"Jang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295255"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.045"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.016"},{"key":"ref9","first-page":"651","article-title":"QT-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conf. Robot Learning (CORL)","author":"Kalashnikov"},{"article-title":"Mt-opt: Continuous multi-task robotic reinforcement learning at scale","year":"2021","author":"Kalashnkov","key":"ref10"},{"article-title":"AutoRT: Embodied foundation models for large scale orchestration of robotic agents","year":"2024","author":"Ahn","key":"ref11"},{"key":"ref12","article-title":"Robocat: A self-improving generalist agent for robotic manipulation","author":"Bousmalis","year":"2023","journal-title":"Trans. Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref14","first-page":"2565","article-title":"Imitating task and motion planning with visuomotor transformers","volume-title":"Conf. Robot Learning (CORL)","author":"Dalal"},{"issue":"1","key":"ref15","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Machine Learning Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560942"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341625"},{"key":"ref18","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Intl. Conf. Machine Learning (ICML)","author":"Sohl-Dickstein"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196862"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3015449"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-22216-0_35"},{"key":"ref22","first-page":"5055","article-title":"Hindsight experience replay","volume-title":"Advances in Neural Information Processing Systems Deep Learning Symposium (NeurIPS)","author":"Andrychowicz"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160763"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3076971"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811798"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196733"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844081"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2013.2289018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919868017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967732"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids43949.2019.9035033"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2014.05.014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561646"},{"key":"ref34","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"Intl. Conf. Machine Learning (ICML)","author":"Finn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191812"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2956365"},{"key":"ref39","first-page":"143","article-title":"Dart: Noise injection for robust imitation learning","volume-title":"Conf. Robot Learning (CORL)","author":"Laskey"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(86)90052-6"},{"key":"ref41","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume-title":"Advances in Neural Information Processing Systems Deep Learning Symposium (NeurIPS)","author":"Pomerleau"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Advances in Neural Information Processing Systems Deep Learning Symposium (NeurIPS)","author":"Wang"},{"key":"ref44","first-page":"1678","article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"Conf. Robot Learning (CORL)","author":"Mandlekar"},{"key":"ref45","article-title":"Mixture density networks","volume-title":"Tech. Rep. NCRG\/94\/004","author":"Bishop","year":"1994"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1_74"},{"article-title":"Discriminator-actor-critic: Addressing sample inefficiency and reward bias in adversarial imitation learning","volume-title":"Intl. Conf. Learning Representations (ICLR)","author":"Kostrikov","key":"ref47"},{"key":"ref48","first-page":"14656","article-title":"What matters for adversarial imitation learning?","volume-title":"Advances in Neural Information Processing Systems Deep Learning Symposium (NeurIPS)","author":"Orsini"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802173.pdf?arnumber=10802173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:59:42Z","timestamp":1735196382000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802173","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}