{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T02:22:29Z","timestamp":1777429349358,"version":"3.51.4"},"reference-count":32,"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\/iros55552.2023.10341985","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"3597-3604","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcement Learning for Robot Navigation with Adaptive Forward Simulation Time (AFST) in a Semi-Markov Model"],"prefix":"10.1109","author":[{"given":"Yu'an","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruosong","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyang","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjian","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangda","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianmin","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891991"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635925"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00108-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5772\/56718"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2869644"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196739"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2007.10.002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3182\/20140824-6-ZA-1003.01143"},{"key":"ref12","author":"Sharma","year":"2017","journal-title":"Learning to repeat: Fine grained action repetition for deep reinforcement learning"},{"key":"ref13","article-title":"Deep reinforcement learning with macro-actions","author":"Durugkar","year":"2016","journal-title":"ar Xiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10918"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281853"},{"key":"ref17","article-title":"Emergence of locomotion behaviours in rich environments","author":"Heess","year":"2017","journal-title":"ar Xiv preprint"},{"key":"ref18","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proceedings of the 4th International Conference on Learning Representations (ICLR-2016)","author":"Schulman","year":"2016"},{"key":"ref19","article-title":"Robust mobile robot navigation using partially-observable semi-markov decision processes","author":"Mahadevan","year":"1999","journal-title":"Internal report"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICARSC.2017.7964088"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/s20174836"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635949"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068662"},{"key":"ref26","first-page":"1430","article-title":"Goal-conditioned rein-forcement learning with imagined subgoals","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML-2021)","author":"Chane-Sane","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-007-9062-7"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"ar Xiv preprint"},{"key":"ref29","article-title":"Lecture 7: Policy gradient","author":"Silver","year":"2015","journal-title":"UCL Course on RL"},{"key":"ref30","author":"Clevert","year":"2016","journal-title":"Fast and accurate deep network learning by exponential linear units (ELUs)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/463"},{"key":"ref32","article-title":"Rectified linear units improve restricted boltzmann machines","volume-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-2010)","author":"Nair"}],"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\/10341985.pdf?arnumber=10341985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T20:22:45Z","timestamp":1705004565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341985\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341985","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}