{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T13:04:11Z","timestamp":1779887051361,"version":"3.53.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"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":[[2025,8,17]]},"DOI":"10.1109\/case58245.2025.11163833","type":"proceedings-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:24:07Z","timestamp":1758648247000},"page":"2730-2737","source":"Crossref","is-referenced-by-count":1,"title":["OffLight: An Offline Multi-Agent Reinforcement Learning Framework for Traffic Signal Control"],"prefix":"10.1109","author":[{"given":"Rohit","family":"Bokade","sequence":"first","affiliation":[{"name":"Northeastern University,Department of Mechanical and Industrial Engineering,Boston,MA,USA,02115"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoning","family":"Jin","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Mechanical and Industrial Engineering,Boston,MA,USA,02115"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116830"},{"key":"ref3","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref4","first-page":"2730","article-title":"Offline reinforcement learning with realizability and single-policy concentrability","volume-title":"Conference on Learning Theory","author":"Zhan"},{"key":"ref5","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358079"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3034419"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671927"},{"key":"ref10","article-title":"The real deal: A review of challenges and opportunities in moving reinforcement learning-based traffic signal control systems towards reality","author":"Chen","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref12","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019"},{"key":"ref14","first-page":"4985","article-title":"Beyond uniform sampling: Offline reinforcement learning with imbalanced datasets","volume":"36","author":"Hong","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3488358"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"ref19","first-page":"4079","article-title":"Attendlight: Universal attention-based reinforcement learning model for traffic signal control","volume":"33","author":"Oroojlooy","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"ref21","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":"ref22","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"and L. Sch\u00e4fer","volume-title":"Multi-Agent Reinforcement Learning: Foundations and Modern Approaches","author":"Albrecht","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/en16145326"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2024.108783"}],"event":{"name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","location":"Los Angeles, CA, USA","start":{"date-parts":[[2025,8,17]]},"end":{"date-parts":[[2025,8,21]]}},"container-title":["2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11163731\/11163732\/11163833.pdf?arnumber=11163833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T14:52:23Z","timestamp":1759243943000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11163833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,17]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/case58245.2025.11163833","relation":{},"subject":[],"published":{"date-parts":[[2025,8,17]]}}}