{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T06:18:53Z","timestamp":1775629133262,"version":"3.50.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000140","name":"U.S. Department of Transportation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000140","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1109\/icmla66185.2025.00159","type":"proceedings-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T19:54:58Z","timestamp":1775591698000},"page":"1046-1051","source":"Crossref","is-referenced-by-count":0,"title":["Offline Reinforcement Learning Benchmark for Variable Speed Limit Control with Real-World Dataset"],"prefix":"10.1109","author":[{"given":"Yuhang","family":"Zhang","sequence":"first","affiliation":[{"name":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212"}]},{"given":"Zhiyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212"}]},{"given":"Marcos","family":"Quinones-Grueiro","sequence":"additional","affiliation":[{"name":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212"}]},{"given":"William","family":"Barbour","sequence":"additional","affiliation":[{"name":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212"}]},{"given":"Gautam","family":"Biswas","sequence":"additional","affiliation":[{"name":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212"}]},{"given":"Daniel","family":"Work","sequence":"additional","affiliation":[{"name":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Traffic flow theory: Characteristics, experimental methods, and numerical techniques","author":"Ni","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3141\/2423-03"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA58977.2023.00033"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/app10144917"},{"key":"ref5","first-page":"530","article-title":"Multiagent traffic management: A reservation-based intersection control mechanism","volume-title":"Proc. Int. Joint Conf. Auton. Agents Multiagent Syst. (AAMAS)","volume":"3","author":"Dresner"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/mits.2025.3592040"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA55696.2022.00044"},{"key":"ref8","author":"Levine","year":"2020","journal-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610308"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1795"},{"key":"ref11","article-title":"Offline reinforcement learning dataset from a field deployed variable speed limit control system","author":"Zhang","year":"2025"},{"key":"ref12","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Yu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3489474"},{"key":"ref14","author":"Yang","year":"2023","journal-title":"Towards robust offline reinforcement learning under diverse data corruption"},{"key":"ref15","author":"Fujimoto","year":"2019","journal-title":"Benchmarking batch deep reinforcement learning algorithms"},{"key":"ref16","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":"ref17","author":"Kostrikov","year":"2021","journal-title":"Offline reinforcement learning with implicit q-learning"},{"key":"ref18","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"},{"issue":"315","key":"ref19","first-page":"1","article-title":"d3rlpy: An offline deep reinforcement learning library","volume":"23","author":"Seno","year":"2022","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2025 International Conference on Machine Learning and Applications (ICMLA)","location":"Boca Raton, FL, USA","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 International Conference on Machine Learning and Applications (ICMLA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11471302\/11471304\/11471420.pdf?arnumber=11471420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:41:48Z","timestamp":1775626908000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11471420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icmla66185.2025.00159","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}