{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:21:12Z","timestamp":1773246072581,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611051","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"13362-13368","source":"Crossref","is-referenced-by-count":4,"title":["Multi-objective Cross-task Learning via Goal-conditioned GPT-based Decision Transformers for Surgical Robot Task Automation"],"prefix":"10.1109","author":[{"given":"Jiawei","family":"Fu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering"}]},{"given":"Yonghao","family":"Long","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering"}]},{"given":"Wang","family":"Wei","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering"}]},{"given":"Qi","family":"Dou","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3284380"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160327"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341608"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196588"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196912"},{"key":"ref6","volume-title":"Reinforcement learning: An introduction.","author":"Sutton","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342180"},{"key":"ref8","article-title":"Adversarial skill chaining for long-horizon robot manipulation via terminal state regularization","volume-title":"5th Annual Conference on Robot Learning","author":"Lee"},{"key":"ref9","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"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","year":"2021"},{"key":"ref11","first-page":"38989","article-title":"Q-learning decision transformer: Leveraging dynamic programming for conditional sequence modelling in offline RL","volume-title":"Proceedings of the 40th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"202","author":"Yamagata"},{"key":"ref12","first-page":"27042","article-title":"Online decision transformer","volume-title":"Proceedings of the 39th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"162","author":"Zheng"},{"key":"ref13","first-page":"27921","article-title":"Multi-game decision transformers","volume":"35","author":"Lee","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","article-title":"Decision transformer under random frame dropping","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635867"},{"key":"ref16","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5650301"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1089\/lap.2013.0304"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8020224"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49439.2021.9551569"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2014.2302385"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2528301"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR.2018.8333301"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3266720"},{"key":"ref26","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref27","article-title":"Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Fixing weight decay regularization in adam","author":"Loshchilov","year":"2018"},{"key":"ref29","first-page":"1719","article-title":"Plas: Latent action space for offline reinforcement learning","volume-title":"Conference on Robot Learning","author":"Zhou"},{"key":"ref30","article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"International Conference on Learning Representations","author":"Kostrikov"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.010"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref35","first-page":"465","article-title":"Integrating behavior cloning and reinforcement learning for improved performance in dense and sparse reward environments","volume-title":"Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems","author":"Goecks"},{"key":"ref36","article-title":"Awac: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020"},{"key":"ref37","article-title":"Med-AIR"},{"issue":"315","key":"ref38","first-page":"1","article-title":"d3rlpy: An offline deep reinforcement learning library","volume":"23","author":"Seno","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611051.pdf?arnumber=10611051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T06:07:22Z","timestamp":1723270042000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611051","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}