{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:30:26Z","timestamp":1730255426702,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610586","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"6836-6842","source":"Crossref","is-referenced-by-count":0,"title":["Generalizing Cooperative Eco-driving via Multi-residual Task Learning"],"prefix":"10.1109","author":[{"given":"Vindula","family":"Jayawardana","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA"}]},{"given":"Sirui","family":"Li","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA"}]},{"given":"Cathy","family":"Wu","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA"}]},{"given":"Yashar","family":"Farid","sequence":"additional","affiliation":[{"name":"Toyota InfoTech Labs and Toyota Motor North America,Mountain View,CA,USA"}]},{"given":"Kentaro","family":"Oguchi","sequence":"additional","affiliation":[{"name":"Toyota InfoTech Labs and Toyota Motor North America,Mountain View,CA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3087314"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ECC55457.2022.9838000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811912"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2018.05.030"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC.2011.5982524"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.12.001"},{"article-title":"Quantifying generalization in reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Cobbe","key":"ref7"},{"key":"ref8","first-page":"23881","article-title":"The impact of task underspecification in evaluating deep reinforcement learning","volume":"35","author":"Jayawardana","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Residual policy learning","year":"2018","author":"Silver","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192770"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146916"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487140"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref18","article-title":"Learning continuous control policies by stochastic value gradients","volume":"28","author":"Heess","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974427"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593995"},{"key":"ref22","article-title":"Contextualize me\u2013the case for context in reinforcement learning","author":"Benjamins","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref24"},{"key":"ref25","article-title":"Learning surrogates for diverse emission models","author":"Sanchez","year":"2022","journal-title":"Tackling Climate Change with Machine Learning, NeurIPS"},{"volume-title":"Moves and other mobile source emissions models","key":"ref26"},{"issue":"11","key":"ref27","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610586.pdf?arnumber=10610586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:51:25Z","timestamp":1723269085000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610586\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610586","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}