{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:37Z","timestamp":1763191717250,"version":"3.45.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228096","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["M-SAT: Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Actions"],"prefix":"10.1109","author":[{"given":"Perusha","family":"Moodley","sequence":"first","affiliation":[]},{"given":"Dhillu","family":"Thambi","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology,Machine Learning Lab,Hyderabad,India"}]},{"given":"Mark","family":"Trovinger","sequence":"additional","affiliation":[{"name":"Mississippi State University,Dept. of Computer Science & Engineering,Starkville,MS,USA"}]},{"given":"Pramod","family":"Kaushik","sequence":"additional","affiliation":[]},{"given":"Praveen","family":"Paruchuri","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology,Machine Learning Lab,Hyderabad,India"}]},{"given":"Xia","family":"Hong","sequence":"additional","affiliation":[{"name":"University of Reading,School of Mathematical, Physical & Computational Sciences,Reading,United Kingdom"}]},{"given":"Benjamin","family":"Rosman","sequence":"additional","affiliation":[{"name":"University of the Witwatersrand,School of Computer Science and Applied Mathematics,Johannesburg,South Africa"}]}],"member":"263","reference":[{"key":"ref1","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Chen","year":"2021"},{"key":"ref2","volume":"abs\/2005.01643","author":"Levine","year":"2020","journal-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Rvs: What is essential for offline RL via supervised learning?","volume-title":"International Conference on Learning Representations","author":"Emmons","key":"ref4"},{"key":"ref5","volume":"abs\/2306.13831","author":"Chevalier-Boisvert","year":"2023","journal-title":"Minigrid & miniworld: Modular & customizable reinforcement learning environments for goal-oriented tasks"},{"key":"ref6","article-title":"Visual reinforcement learning with imagined goals","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Nair","year":"2018"},{"key":"ref7","volume":"abs\/2004.07219","author":"Fu","year":"2020","journal-title":"D4RL: datasets for deep data-driven reinforcement learning"},{"article-title":"AlphaStar unplugged: Large-Scale offline reinforcement learning","year":"2023","author":"Mathieu","key":"ref8"},{"key":"ref9","article-title":"A generalist agent","volume-title":"Transactions on Machine Learning Research","author":"Reed","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_27"},{"key":"ref11","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Jaegle"},{"article-title":"Vima: Robot manipulation with multimodal prompts","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Jiang","key":"ref12"},{"article-title":"Know your action set: Learning action relations for reinforcement learning","volume-title":"ICLR","author":"Jain","key":"ref13"},{"key":"ref14","volume":"abs\/2307.02484","author":"Wu","year":"2023","journal-title":"Elastic decision transformer"},{"key":"ref15","first-page":"24631","article-title":"Prompting decision transformer for Few-Shot policy generalization","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Xu"},{"article-title":"Chain-of-thought predictive control","volume-title":"Workshop on Reincarnating Reinforcement Learning at ICLR 2023","author":"Jia","key":"ref16"},{"key":"ref17","volume":"abs\/1312.5602","author":"Mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"article-title":"Voyager: An open-ended embodied agent with large language models","year":"2023","author":"Wang","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231687"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2205582119"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.semeval-1.112"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3389\/fenrg.2022.952420"},{"article-title":"Reinforcement learning with un-supervised auxiliary tasks","volume-title":"International Conference on Learning Representations","author":"Jaderberg","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179433"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.289"},{"key":"ref28","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown","year":"2020"},{"article-title":"Unleashing the power of pre-trained language models for offline reinforcement learning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Shi","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"article-title":"What improves the generalization of graph transformer? a theoretical dive into self-attention and positional encoding","volume-title":"NeurIPS 2023 Workshop: New Frontiers in Graph Learning","author":"Li","key":"ref31"},{"key":"ref32","volume":"abs\/2307.10936","author":"Boige","year":"2023","journal-title":"PASTA: Pretrained Action-State transformer agents"},{"article-title":"For sale: State-action representation learning for deep reinforcement learning","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Fujimoto","key":"ref33"},{"key":"ref34","volume":"abs\/2305.19466","author":"Kazemnejad","year":"2023","journal-title":"The impact of positional encoding on length generalization in transformers"},{"key":"ref35","article-title":"A mathematical framework for transformer circuits","author":"Elhage","year":"2021","journal-title":"Transformer Circuits Thread"},{"key":"ref36","article-title":"Towards monosemanticity: Decomposing language models with dictionary learning","volume-title":"Transformer Circuits Thread","author":"Bricken","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-40807-0"},{"article-title":"Circuitsviz","year":"2022","author":"Cooney","key":"ref38"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228096.pdf?arnumber=11228096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:26:48Z","timestamp":1763191608000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228096\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228096","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}