{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T20:51:19Z","timestamp":1789419079716,"version":"build-2803163510"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Major Research Plan of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92048301"],"award-info":[{"award-number":["92048301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341718","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"1-7","source":"Crossref","is-referenced-by-count":4,"title":["Effective Traffic Signal Control with Offline-to-Online Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Jinming","family":"Ma","sequence":"first","affiliation":[{"name":"The School of Computer Science and Technology, University of Science and Technology of China,Hefei,Anhui,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"The School of Computer Science and Technology, University of Science and Technology of China,Hefei,Anhui,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"ref4","article-title":"Feudal multi-agent reinforcement learning with adaptive network partition for traffic signal control","author":"Ma","year":"2022","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Bench-marking batch deep reinforcement learning algorithms","author":"Fujimoto","year":"2019","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"1258","article-title":"Learning to coordinate from offline datasets with uncoordinated behavior policies","volume-title":"Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems","author":"Ma"},{"key":"ref10","first-page":"1239","article-title":"Less is more: Refining datasets for offline reinforcement learning with reward machines","volume-title":"Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems","author":"Sun"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357900"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5113-5_3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6243-9_2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref16","first-page":"816","article-title":"Feudal multi-agent deep reinforcement learning for traffic signal control","volume-title":"Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS)","author":"Ma"},{"key":"ref17","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"A survey on traffic signal control methods","author":"Wei","year":"2019","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref20","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref21","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume":"33","author":"Laskin","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"907","article-title":"S4rl: Surprisingly simple self-supervision for offline reinforcement learning in robotics","volume-title":"Conference on Robot Learning","author":"Sinha"},{"key":"ref23","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341718.pdf?arnumber=10341718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:24:15Z","timestamp":1703031855000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341718\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341718","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}