{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:39:28Z","timestamp":1757608768118,"version":"3.44.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127601","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1451-1458","source":"Crossref","is-referenced-by-count":0,"title":["Duolingo: Dynamics Utilization for Online Translation of Actions"],"prefix":"10.1109","author":[{"given":"Karthikeya","family":"Vemuri","sequence":"first","affiliation":[{"name":"University of Washington"}]},{"given":"Alan","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Arnav","family":"Thareja","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Zoey","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Ian","family":"Good","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Jeffrey","family":"Lipton","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Abhishek","family":"Gupta","sequence":"additional","affiliation":[{"name":"University of Washington"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00812"},{"key":"ref2","first-page":"17","article-title":"Deep learning of representations for unsupervised and transfer learning","volume-title":"In Proceedings of ICML workshop on unsupervised and transfer learning","author":"Bengio","year":"2012"},{"key":"ref3","first-page":"1240","article-title":"Online learned continual compression with adaptive quantization modules","volume-title":"In International conference on machine learning","author":"Caccia","year":"2020"},{"key":"ref4","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"In International conference on machine learning","author":"Finn","year":"2017"},{"key":"ref5","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"In International conference on machine learning","author":"Fujimoto","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/robosoft54090.2022.9762141"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9812156"},{"key":"ref8","first-page":"18611870","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"In International conference on machine learning","author":"Haarnoja","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197124"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1561\/2400000013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273565"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref14","article-title":"Actor-critic algorithms","volume":"12","author":"Konda","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2959445"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar4586"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610040"},{"key":"ref21","article-title":"Variational continual learning","author":"Nguyen","year":"2017","journal-title":"arXiv preprint"},{"journal-title":"Recurrent model-free rl can be a strong baseline for many pomdps","year":"2022","author":"Ni","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5981"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2018.8460528"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273592"},{"key":"ref29","article-title":"Online structured laplace approximations for overcoming catastrophic forgetting","volume":"31","author":"Ritter","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","volume-title":"In Conference on robot learning","author":"Rusu","year":"2017"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref33","first-page":"4528","article-title":"Progress & compress: A scalable framework for continual learning","volume-title":"In International conference on machine learning","author":"Schwarz","year":"2018"},{"key":"ref34","article-title":"Continual learning with deep generative replay","volume":"30","author":"Shin","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/robosoft55895.2023.10121989"},{"journal-title":"Gymnasium","year":"2023","author":"Towers","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2021.3052422"},{"key":"ref38","article-title":"Memory replay with data compression for continual learning","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367329"},{"key":"ref40","article-title":"Memory replay gans: Learning to generate new categories without forgetting","volume":"31","author":"Wu","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10342379"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127601.pdf?arnumber=11127601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:18:52Z","timestamp":1756880332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127601","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}