{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:42:31Z","timestamp":1762368151595,"version":"build-2065373602"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"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":[[2025,8,31]]},"DOI":"10.1109\/mlsp62443.2025.11204264","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:52Z","timestamp":1761326152000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["State Prediction for Offline Reinforcement Learning via Sequence-to-Sequence Modeling"],"prefix":"10.1109","author":[{"given":"Abdelghani","family":"Ghanem","sequence":"first","affiliation":[{"name":"International University of Rabat,TICLab, College of Engineering and Architecture,Morocco"}]},{"given":"Mounir","family":"Ghogho","sequence":"additional","affiliation":[{"name":"University Mohammed VI Polytechnic,College of Computing,Morocco"}]},{"given":"Philippe","family":"Ciblat","sequence":"additional","affiliation":[{"name":"Institut Polytechnique de Paris,LTCI,Department of Image, Data, Signal, Telecom Paris,France"}]}],"member":"263","reference":[{"journal-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","year":"2020","author":"Levine","key":"ref1"},{"key":"ref2","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446781"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446266"},{"journal-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref5"},{"key":"ref6","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"journal-title":"Is conditional generative modeling all you need for decisionmaking?","year":"2023","author":"Ajay","key":"ref7"},{"journal-title":"2023, Course notes for MIT 6.832","article-title":"Underactuated robotics: Algorithms for walking, running, swimming, flying, and manipulation","author":"Tedrake","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP58920.2024.10734755"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP55844.2023.10285895"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP58920.2024.10734749"},{"key":"ref12","first-page":"2226","article-title":"A trajectory is worth three sentences: multimodal transformer for offline reinforcement learning","volume-title":"Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence","volume":"216","author":"Wang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP58920.2024.10734745"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP58920.2024.10734819"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP58920.2024.10734776"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095442"},{"journal-title":"Learning to poke by poking: Experiential learning of intuitive physics","year":"2017","author":"Agrawal","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00278"},{"journal-title":"D4rl: Datasets for deep data-driven reinforcement learning","year":"2021","author":"Fu","key":"ref20"},{"journal-title":"Openai gym","year":"2016","author":"Brockman","key":"ref21"},{"journal-title":"Conservative q-learning for offline reinforcement learning","year":"2020","author":"Kumar","key":"ref22"},{"journal-title":"Offline reinforcement learning with implicit q-learning","year":"2021","author":"Kostrikov","key":"ref23"}],"event":{"name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","start":{"date-parts":[[2025,8,31]]},"location":"Istanbul, Turkiye","end":{"date-parts":[[2025,9,3]]}},"container-title":["2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204201\/11204202\/11204264.pdf?arnumber=11204264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:37:29Z","timestamp":1762367849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/mlsp62443.2025.11204264","relation":{},"subject":[],"published":{"date-parts":[[2025,8,31]]}}}