{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T18:21:09Z","timestamp":1773858069984,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342230","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"1661-1666","source":"Crossref","is-referenced-by-count":10,"title":["Hierarchical Decision Transformer"],"prefix":"10.1109","author":[{"given":"Andr\u00e9","family":"Correia","sequence":"first","affiliation":[{"name":"NOVA LINCS, Universidade da Beira Interior, R. Marquês de Ávila e Bolama 6201–001,Covilhã,Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis A.","family":"Alexandre","sequence":"additional","affiliation":[{"name":"NOVA LINCS, Universidade da Beira Interior, R. Marquês de Ávila e Bolama 6201–001,Covilhã,Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","article-title":"Stabilizing deep q-learning with con-vnets and vision transformers under data augmentation","volume":"34","author":"Hansen","year":"2021","journal-title":"Advances In Neural Information Processing Systems"},{"key":"ref3","article-title":"Conservative data sharing for multi-task offline reinforcement learning","volume":"34","author":"Yu","year":"2021","journal-title":"Advances In Neural Information Processing Systems"},{"key":"ref4","first-page":"1430","article-title":"Goal-conditioned reinforce-ment learning with imagined subgoals","volume-title":"International Conference On Machine Learning","author":"Chane-Sane"},{"key":"ref5","article-title":"Decision transformer: Reinforce-ment learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances In Neural Information Processing Systems"},{"key":"ref6","author":"Fu","year":"2020","journal-title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning"},{"key":"ref7","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"Mandlekar","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref10","author":"Ross","year":"2011","journal-title":"A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196935"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918784350"},{"key":"ref13","article-title":"Accelerating reinforcement learning with learned skill priors","author":"Pertsch","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Learning from trajectories via subgoal discovery","volume":"32","author":"Paul","year":"2019","journal-title":"Advances In Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"ref16","article-title":"Data-efficient hierarchical reinforcement learning","volume":"31","author":"Nachum","year":"2018","journal-title":"Advances In Neural Information Processing Systems"},{"key":"ref17","first-page":"17321","article-title":"Long-horizon visual planning with goal-conditioned hierarchical predictors","volume":"33","author":"Pertsch","year":"2020","journal-title":"Advances In Neural Information Processing Systems"},{"key":"ref18","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances In Neural Information Processing Systems"},{"key":"ref19","article-title":"Reinforcement Learning as One Big Sequence Modeling Problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances In Neural Information Processing Systems"},{"issue":"9","key":"ref20","article-title":"Others Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342230.pdf?arnumber=10342230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:27:25Z","timestamp":1703014045000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342230\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342230","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}