{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:11:56Z","timestamp":1777655516420,"version":"3.51.4"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802437","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"7469-7476","source":"Crossref","is-referenced-by-count":5,"title":["Predictive Coding for Decision Transformer"],"prefix":"10.1109","author":[{"given":"Tung M.","family":"Luu","sequence":"first","affiliation":[{"name":"KAIST (Korea Advanced Institute of Science and Technology),School of Electrical Engineering,Daejeon,Republic of Korea"}]},{"given":"Donghoon","family":"Lee","sequence":"additional","affiliation":[{"name":"KAIST (Korea Advanced Institute of Science and Technology),School of Electrical Engineering,Daejeon,Republic of Korea"}]},{"given":"Chang D.","family":"Yoo","sequence":"additional","affiliation":[{"name":"KAIST (Korea Advanced Institute of Science and Technology),School of Electrical Engineering,Daejeon,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363436"},{"key":"ref2","article-title":"Waypoint transformer: Reinforcement learning via supervised learning with intermediate targets","volume-title":"NeurIPS","author":"Badrinath"},{"key":"ref3","article-title":"Beit: Bert pretraining of image transformers","author":"Bao","year":"2021"},{"key":"ref4","article-title":"When does return-conditioned supervised learning work for offline reinforcement learning?","volume-title":"NeurIPS","author":"Brandfonbrener"},{"key":"ref5","article-title":"Language models are few-shot learners","volume-title":"NeurIPS","author":"Brown"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","article-title":"Uni [mask]: Unified inference in sequential decision problems","volume-title":"NeurIPS","author":"Carroll"},{"key":"ref8","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"NeurIPS","author":"Chen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342230"},{"key":"ref11","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref12","article-title":"Goal-conditioned imitation learning","volume-title":"NeurIPS","author":"Ding"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref14","article-title":"Rvs: What is essential for offline rl via supervised learning?","volume-title":"ICLR","author":"Emmons"},{"key":"ref15","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref16","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"ICML","author":"Fujimoto"},{"key":"ref17","article-title":"Generalized decision transformer for offline hindsight information matching","volume-title":"ICLR","author":"Furuta"},{"key":"ref18","article-title":"Reinforcement learning from passive data via latent intentions","volume-title":"ICML","author":"Ghosh"},{"key":"ref19","article-title":"Learning to reach goals via iterated supervised learning","volume-title":"ICLR","author":"Ghosh"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197408"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref22","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume-title":"NeurIPS","author":"Janner"},{"key":"ref23","article-title":"Efficient planning in a compact latent action space","volume-title":"ICLR","author":"Jiang"},{"key":"ref24","article-title":"Learning to achieve goals","volume-title":"IJCAI","author":"Kaelbling"},{"key":"ref25","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"CoRL","author":"Kalashnikov"},{"key":"ref26","article-title":"Morel: Model-based offline reinforcement learning","volume-title":"NeurIPS","author":"Kidambi"},{"key":"ref27","article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"ICLR","author":"Kostrikov"},{"key":"ref28","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume-title":"NeurIPS","author":"Kumar"},{"key":"ref29","article-title":"When should we prefer offline reinforcement learning over behavioral cloning?","volume-title":"ICLR","author":"Kumar"},{"key":"ref30","article-title":"Reward-conditioned policies","author":"Kumar","year":"2019"},{"key":"ref31","article-title":"Conservative q-learning for offline reinforcement learning","volume-title":"NeurIPS","author":"Kumar"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref33","article-title":"Masked autoencoding for scalable and generalizable decision making","volume-title":"NeurIPS","author":"Liu"},{"key":"ref34","article-title":"Provably good batch off-policy reinforcement learning without great exploration","volume-title":"NeurIPS","author":"Liu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3069975"},{"key":"ref36","article-title":"Visual reinforcement learning with imagined goals","volume-title":"NeurIPS","author":"Nair"},{"key":"ref37","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"ICML","author":"Ng"},{"key":"ref38","article-title":"Hiql: Offline goal-conditioned rl with latent states as actions","volume-title":"NeurIPS","author":"Park"},{"key":"ref39","article-title":"Data-efficient deep reinforcement learning for dexterous manipulation","author":"Popov","year":"2017"},{"key":"ref40","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref41","author":"Radford","year":"2019","journal-title":"Language models are unsupervised multitask learners"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref43","article-title":"Training agents using upside-down reinforcement learning","author":"Srivastava","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref45","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani"},{"key":"ref46","article-title":"Masked trajectory models for prediction, representation, and control","volume-title":"ICML","author":"Wu"},{"key":"ref47","article-title":"Future-conditioned unsupervised pretraining for decision transformer","volume-title":"ICML","author":"Xie"},{"key":"ref48","article-title":"A policy-guided imitation approach for offline reinforcement learning","volume-title":"NeurIPS","author":"Xu"},{"key":"ref49","article-title":"Prompting decision transformer for few-shot policy generalization","volume-title":"ICML","author":"Xu"},{"key":"ref50","article-title":"Q-learning decision transformer: Leveraging dynamic programming for conditional sequence modelling in offline rl","volume-title":"ICML","author":"Yamagata"},{"key":"ref51","article-title":"Dichotomy of control: Separating what you can control from what you cannot","volume-title":"ICLR","author":"Yang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.003"},{"key":"ref53","article-title":"Mopo: Model-based offline policy optimization","volume-title":"NeurIPS","author":"Yu"},{"key":"ref54","article-title":"Online decision transformer","volume-title":"ICML","author":"Zheng"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802437.pdf?arnumber=10802437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:00:46Z","timestamp":1735196446000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802437\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802437","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}