{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:24:12Z","timestamp":1766067852763},"reference-count":38,"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\/iros55552.2023.10342180","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"source":"Crossref","is-referenced-by-count":4,"title":["Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot"],"prefix":"10.1109","author":[{"given":"Tao","family":"Huang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,The Department of Computer Science and Engineering"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,The Department of Computer Science and Engineering"}]},{"given":"Wang","family":"Wei","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,The Department of Computer Science and Engineering"}]},{"given":"Jianan","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,The Department of Computer Science and Engineering"}]},{"given":"Yonghao","family":"Long","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,The Department of Computer Science and Engineering"}]},{"given":"Qi","family":"Dou","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,The Department of Computer Science and Engineering"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1142\/9789813232266_0010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ismr48346.2021.9661573"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref4","article-title":"Learning by playing solving sparse reward tasks from scratch","volume-title":"International Conference on Machine Learning (ICML)","author":"Riedmiller","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref6","article-title":"Learning to coordinate manipulation skills via skill behavior diversification","volume-title":"International conference on learning representations (ICLR)","author":"Lee","year":"2020"},{"key":"ref7","article-title":"Composing complex skills by learning transition policies","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lee","year":"2019"},{"key":"ref8","article-title":"Training transition policies via distribution matching for complex tasks","volume-title":"International Conference on Learning Representations (ICLR)","author":"BYUN","year":"2022"},{"key":"ref9","article-title":"Adversarial skill chaining for long-horizon robot manipulation via terminal state regularization","volume-title":"Conference on Robot Learning (CoRL)","author":"Lee","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275048"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635867"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989275"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT.2019.8755235"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SYSCON.2019.8836924"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341710"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636175"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR48346.2021.9661514"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812379"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160327"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR46387.2019.8981619"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341382"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636432"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49439.2021.9551569"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN47096.2020.9223543"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812393"},{"key":"ref26","article-title":"Skill discovery in continuous reinforcement learning domains using skill chaining","author":"Konidaris","year":"2009","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911428653"},{"key":"ref28","article-title":"Option discovery using deep skill chaining","volume-title":"International Conference on Learning Representations (ICLR)","author":"Bagaria","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/298"},{"key":"ref30","article-title":"Divide-and-conquer reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ghosh","year":"2018"},{"key":"ref31","author":"Nasiriany","year":"2019","journal-title":"Planning with goal-conditioned policies"},{"key":"ref32","article-title":"Modular multitask reinforcement learning with policy sketches","volume-title":"International Conference on Machine Learning (ICML)","author":"Andreas","year":"2017"},{"key":"ref33","article-title":"Universal value function approximators","volume-title":"International Conference on Machine Learning (ICML)","author":"Schaul","year":"2015"},{"key":"ref34","article-title":"Self-imitation learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Oh","year":"2018"},{"key":"ref35","article-title":"Awac: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Goal-conditioned imitation learning","author":"Ding","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref37","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning (ICML)","author":"Haarnoja","year":"2018"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kingma","year":"2015"}],"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\/10342180.pdf?arnumber=10342180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:19:21Z","timestamp":1703031561000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342180","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}