{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:46:15Z","timestamp":1791996375127,"version":"4.4.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-1847056"],"award-info":[{"award-number":["ECCS-1847056"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161368","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"7205-7211","source":"Crossref","is-referenced-by-count":9,"title":["Self-Adaptive Driving in Nonstationary Environments through Conjectural Online Lookahead Adaptation"],"prefix":"10.1109","author":[{"given":"Tao","family":"Li","sequence":"first","affiliation":[{"name":"New York University,Department of Electrical and Computer Engineering,Brooklyn,NY,USA,11201"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haozhe","family":"Lei","sequence":"additional","affiliation":[{"name":"New York University,Department of Electrical and Computer Engineering,Brooklyn,NY,USA,11201"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanyan","family":"Zhu","sequence":"additional","affiliation":[{"name":"New York University,Department of Electrical and Computer Engineering,Brooklyn,NY,USA,11201"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"264","author":"choi","year":"2001","journal-title":"Hidden-Mode Markov Decision Processes for Nonstationary Sequential Decision Making"},{"key":"ref35","article-title":"Deep Reinforcement Learning amidst Lifelong Non-Stationarity","author":"xie","year":"2020","journal-title":"ArXiv"},{"key":"ref12","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref34","first-page":"1920","volume":"97","author":"finn","year":"2019","journal-title":"Online Meta-Learning"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref37","author":"palanisamy","year":"2019","journal-title":"Multi-agent connected autonomous driving using deep reinforcement learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2022.03.003"},{"key":"ref36","first-page":"16532","article-title":"Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning","volume":"33","author":"caccia","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"ref30","article-title":"End-to-end deep reinforcement learning for lane keeping assist","volume":"abs 1612 4340","author":"sallab","year":"2016","journal-title":"ArXiv"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TPAMI.2021.3079209","article-title":"Meta-Learning in Neural Networks: A Survey","volume":"pp","author":"hospedales","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00084"},{"key":"ref10","first-page":"1","volume":"78","author":"dosovitskiy","year":"2017","journal-title":"CARLA An Open Urban Driving Simulator"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2106158"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref1","first-page":"627","article-title":"A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning","volume":"15","author":"ross","year":"2011","journal-title":"JMLR Workshop and Conference Proceedings"},{"key":"ref17","article-title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","author":"nagabandi","year":"2018","journal-title":"ArXiv"},{"key":"ref39","author":"schulman","year":"2017","journal-title":"Equivalence between policy gradients and soft q-learning"},{"key":"ref16","author":"mnih","year":"2016","journal-title":"Asynchronous methods for deep reinforcement learning"},{"key":"ref38","author":"palanisamy","year":"2018","journal-title":"Hands-On Intelligent Agents with OpenAI Gym Your Guide to Developing AI Agents Using Deep Reinforcement Learning"},{"key":"ref19","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume":"97","author":"rakelly","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref18","article-title":"Meta-sgd: Learning to learn quickly for few-shot learning","author":"li","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref24","first-page":"11909","article-title":"Generalized Proximal Policy Optimization with Sample Reuse","volume":"34","author":"queeney","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Monte-Carlo Planning in Large POMDPs","volume":"23","author":"silver","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref26","first-page":"22","volume":"70","author":"achiam","year":"2017","journal-title":"Constrained Policy Optimization"},{"key":"ref25","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"Proceedings of The 32nd International Conference on Machine Learning"},{"key":"ref20","first-page":"17571","article-title":"Continuous Meta-Learning without Tasks","volume":"33","author":"harrison","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1613\/jair.2567","article-title":"Online Planning Algorithms for POMDPs","volume":"32","author":"ross","year":"2014","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2078"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"ref27","article-title":"Deep Residual Learning for Image Recognition","author":"he","year":"2015","journal-title":"ArXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105157"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CISS50987.2021.9400319"},{"key":"ref7","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in Neural Information Processing Systems 12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3459991"},{"key":"ref4","first-page":"1","article-title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","volume":"pp","author":"kiran","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref3","article-title":"The Confluence of Networks, Games and Learning","author":"li","year":"2021","journal-title":"ArXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2019.8918816"},{"key":"ref5","first-page":"1","article-title":"Interpretable End-to-End Urban Autonomous Driving With Latent Deep Reinforcement Learning","volume":"pp","author":"chen","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref40","author":"smith","year":"2017","journal-title":"Super-convergence Very fast training of neural networks using large learning rates"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161368.pdf?arnumber=10161368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:34:00Z","timestamp":1690220040000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161368\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161368","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}