{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:15:51Z","timestamp":1774120551031,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T00:00:00Z","timestamp":1719273600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T00:00:00Z","timestamp":1719273600000},"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":[[2024,6,25]]},"DOI":"10.23919\/ecc64448.2024.10590895","type":"proceedings-article","created":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T17:48:23Z","timestamp":1721843303000},"page":"1399-1406","source":"Crossref","is-referenced-by-count":6,"title":["Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning"],"prefix":"10.23919","author":[{"given":"Carolin","family":"Schmidt","sequence":"first","affiliation":[{"name":"Technical University of Denmark,Department of Technology, Management and Economics,Kongens Lyngby,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Gammelli","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Aeronautics and Astronautics,Stanford,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francisco Camara","family":"Pereira","sequence":"additional","affiliation":[{"name":"Technical University of Denmark,Department of Technology, Management and Economics,Kongens Lyngby,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Filipe","family":"Rodrigues","sequence":"additional","affiliation":[{"name":"Technical University of Denmark,Department of Technology, Management and Economics,Kongens Lyngby,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"68% of the world population projected to live in urban areas by 2050","author":"Aff","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102626"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3046995"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683135"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539180"},{"key":"ref6","first-page":"1","author":"Levine","year":"2020","journal-title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981319"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.05.003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460966"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103852"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917533"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmse.2021.12.004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103289"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467096"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539141"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539095"},{"key":"ref18","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"80","author":"Haarnoja"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3250269"},{"key":"ref20","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kumar","year":"2020"},{"key":"ref21","author":"Fu","year":"2020","journal-title":"D4rl: Datasets for deep data-driven reinforcement learning"},{"key":"ref22","author":"Nakamoto","year":"2023","journal-title":"Cal-ql: Calibrated offline rl pretraining for efficient online fine-tuning"},{"key":"ref23","article-title":"Graph reinforcement learning for network control via bi-level optimization","volume-title":"Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA","volume":"202","author":"Gammelli","year":"2023"},{"key":"ref24","article-title":"NeoRL: A near real-world benchmark for offline reinforcement learning","author":"Qin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","article-title":"Understanding the effects of dataset characteristics on offline reinforcement learning","author":"Schweighofer","year":"2021","journal-title":"Deep RL Workshop NeurIPS 2021"},{"key":"ref26","article-title":"Empirical study of off-policy policy evaluation for reinforcement learning","volume":"1","author":"Voloshin","year":"2021","journal-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks"}],"event":{"name":"2024 European Control Conference (ECC)","location":"Stockholm, Sweden","start":{"date-parts":[[2024,6,25]]},"end":{"date-parts":[[2024,6,28]]}},"container-title":["2024 European Control Conference (ECC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10590709\/10590710\/10590895.pdf?arnumber=10590895","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T05:48:41Z","timestamp":1721886521000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10590895\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,25]]},"references-count":26,"URL":"https:\/\/doi.org\/10.23919\/ecc64448.2024.10590895","relation":{},"subject":[],"published":{"date-parts":[[2024,6,25]]}}}