{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:40:11Z","timestamp":1755841211245,"version":"3.44.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"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","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,8]]},"DOI":"10.23919\/acc63710.2025.11107876","type":"proceedings-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:17:51Z","timestamp":1755800271000},"page":"3473-3478","source":"Crossref","is-referenced-by-count":0,"title":["Trajectory-Based Automata Learning for Offline Reinforcement Learning"],"prefix":"10.23919","author":[{"given":"Shayan Meshkat","family":"Alsadat","sequence":"first","affiliation":[{"name":"Arizona State University,Faculty of Mechanical Engineering,Tempe,Arizona,USA"}]},{"given":"Zhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Arizona State University,Faculty of Mechanical Engineering,Tempe,Arizona,USA"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","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":"ref3","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"International conference on machine learning","author":"Agarwal"},{"key":"ref4","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International conference on machine learning","author":"Fujimoto"},{"article-title":"Behavior regularized offline reinforcement learning","year":"2019","author":"Wu","key":"ref5"},{"article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","year":"2020","author":"Levine","key":"ref6"},{"article-title":"Identifying co-adaptation of algorithmic and implementational innovations in deep reinforcement learning: A taxonomy and case study of inference-based algorithms","year":"2021","author":"Furuta","key":"ref7"},{"key":"ref8","first-page":"2107","article-title":"Using reward machines for high-level task specification and decomposition in reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Icarte"},{"key":"ref9","first-page":"643","article-title":"Expediting reinforcement learning by incorporating knowledge about temporal causality in the environment","volume-title":"Causal Learning and Reasoning","author":"Corazza","year":"2024"},{"key":"ref10","first-page":"5305","article-title":"Safe policy improvement with baseline bootstrapping","volume-title":"Proceedings of the 33rd Conference on Neural Information Processing Systems","author":"Laroche"},{"key":"ref11","first-page":"11739","article-title":"Alleviating extrapolation error in reinforcement learning with approximate models","volume-title":"Proceedings of the 33rd Conference on Neural Information Processing Systems","author":"Nachum"},{"journal-title":"Offline reinforcement learning with implicit q-learning","year":"2021","author":"Kostrikov","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128170"},{"key":"ref14","first-page":"12","article-title":"Robot learning from demonstration","volume-title":"Proceedings of the Fourteenth International Conference on Machine Learning","author":"Atkeson"},{"journal-title":"Integrating behavior cloning and reinforcement learning for improved performance in sparse-reward environments","year":"2020","author":"Goecks","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"journal-title":"Self-imitation learning via generative adversarial nets","year":"2020","author":"G\u00fcl\u00e7ehre","key":"ref18"},{"article-title":"Policy optimization via imitation learning","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Kang","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2869644"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icra48506.2021.9561333"},{"issue":"1","key":"ref22","first-page":"927","article-title":"An overview of association rule mining algorithms","volume":"5","author":"Kumbhare","year":"2014","journal-title":"International Journal of Computer Science and Information Technologies"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17096"},{"issue":"1","key":"ref24","first-page":"1","article-title":"Data quality considerations for big data and machine learning: Going beyond data cleaning and transformations","volume":"10","author":"Gudivada","year":"2017","journal-title":"International Journal on Advances in Software"},{"article-title":"Accelerating online reinforcement learning with offline datasets","year":"2020","author":"Nair","key":"ref25"},{"volume-title":"Fast algorithms for mining association rules","year":"1994","author":"Agrawal","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41591-8_2"},{"article-title":"Attengluco: Multimodal transformer-based blood glucose forecasting on ai-readi dataset","year":"2025","author":"Farahmand","key":"ref28"}],"event":{"name":"2025 American Control Conference (ACC)","start":{"date-parts":[[2025,7,8]]},"location":"Denver, CO, USA","end":{"date-parts":[[2025,7,10]]}},"container-title":["2025 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11107441\/11107442\/11107876.pdf?arnumber=11107876","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:25:02Z","timestamp":1755840302000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11107876\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,8]]},"references-count":28,"URL":"https:\/\/doi.org\/10.23919\/acc63710.2025.11107876","relation":{},"subject":[],"published":{"date-parts":[[2025,7,8]]}}}