{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T16:09:29Z","timestamp":1790698169961,"version":"4.1.0"},"reference-count":37,"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\/iros58592.2024.10801303","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"7477-7483","source":"Crossref","is-referenced-by-count":3,"title":["Steering Decision Transformers via Temporal Difference Learning"],"prefix":"10.1109","author":[{"given":"Hao-Lun","family":"Hsu","sequence":"first","affiliation":[{"name":"Duke University,Department of Computer Science,Durham,NC,USA,27708"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alper Kamil","family":"Bozkurt","sequence":"additional","affiliation":[{"name":"Duke University,Department of Computer Science,Durham,NC,USA,27708"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juncheng","family":"Dong","sequence":"additional","affiliation":[{"name":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qitong","family":"Gao","sequence":"additional","affiliation":[{"name":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vahid","family":"Tarokh","sequence":"additional","affiliation":[{"name":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miroslav","family":"Pajic","sequence":"additional","affiliation":[{"name":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref2","article-title":"Benchmarking offline reinforcement learning on real-robot hardware","volume-title":"International Conference on Learning Representations","author":"G\u00fcrtler"},{"key":"ref3","article-title":"A workflow for offline model-free robotic rl","volume-title":"Conference on Robot Learning","author":"Kumar"},{"key":"ref4","article-title":"Cog: Connecting new skills to past experience with offline reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Singh"},{"key":"ref5","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref6","article-title":"D4rl:datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29302"},{"key":"ref8","article-title":"Robonet: Large-scale multi-robot learning","volume-title":"CoRL 2019","volume":"100","author":"Dasari"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref10","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Chen"},{"key":"ref11","article-title":"Goal-conditioned imitation learning","volume-title":"Advances in Neural Information Proc. Sys","author":"Ding"},{"key":"ref12","article-title":"Learning to reach goals via iterated supervised learning","volume-title":"International Conference on Learning Representations","author":"Ghosh"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-6754-9_14942"},{"key":"ref15","article-title":"You can\u2019t count on luck: Why decision transformers fail in stochastic environments","author":"Paster","year":"2022"},{"key":"ref16","first-page":"22270","article-title":"Addressing optimism bias in sequence modeling for reinforcement learning","volume-title":"39th Int. Conf. on Machine Learning","volume":"162","author":"Villaflor"},{"key":"ref17","article-title":"Q-learning decision transformer: Leveraging dynamic programming for conditional sequence modelling in offline RL","volume-title":"International Conference on Machine Learning","author":"Yamagata"},{"key":"ref18","article-title":"Elastic decision transformer","volume-title":"37th Conference on Neural Information Processing Systems","author":"Wu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341628"},{"key":"ref20","article-title":"Actor-critic algorithms","volume-title":"Advances in neural information processing systems","volume":"12","author":"Konda"},{"key":"ref21","first-page":"1","article-title":"An open urban driving simulator","volume-title":"Conf. on Robot Learning","author":"Dosovitskiy"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1109\/IROS58592.2024.10801303","article-title":"Steering decision transformers via temporal difference learning","volume-title":"tech. rep.","author":"Hsu","year":"2024"},{"key":"ref23","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref24","article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"Int. Conf. on Learning Repr. (ICLR)","author":"Kostrikov"},{"key":"ref25","first-page":"15293","article-title":"Causal transformer for estimating counterfactual outcomes","volume-title":"Int. Conf. on Machine Learning","author":"Melnychuk"},{"key":"ref26","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume-title":"Advances in Neural Information Processing Systems","author":"Janner"},{"key":"ref27","article-title":"Conservative q-learning for offline reinforcement learning","author":"Kumar","year":"2020"},{"key":"ref28","article-title":"Mildly conservative q-learning for offline reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","author":"Lyu"},{"key":"ref29","article-title":"Contrastive learning as a reinforcement learning algorithm","author":"Eysenbach","year":"2022"},{"key":"ref30","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref32","article-title":"Dichotomy of control: Separating what you can control from what you cannot","volume-title":"International Conference on Learning Representations","author":"Yang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160497"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00996"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161034"},{"key":"ref36","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2020"},{"key":"ref37","article-title":"Q-transformer: Scalable offline reinforcement learning via autoregressive q-functions","volume-title":"Conference on robot learning, Proc. of Machine Learning Research","author":"Chebotar"}],"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\/10801303.pdf?arnumber=10801303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T19:07:06Z","timestamp":1735240026000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801303","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}