{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T05:08:37Z","timestamp":1746508117782,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1109\/mfi.2017.8170388","type":"proceedings-article","created":{"date-parts":[[2017,12,11]],"date-time":"2017-12-11T22:39:52Z","timestamp":1513031992000},"page":"602-607","source":"Crossref","is-referenced-by-count":7,"title":["Deep reinforcement learning algorithms for steering an underactuated ship"],"prefix":"10.1109","author":[{"given":"Le Pham","family":"Tuyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abu","family":"Layek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngo Anh","family":"Vien","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"TaeChoong","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Hierarchical policy gradient algorithms","author":"ghavamzadeh","year":"2003","journal-title":"Proceedings of the 20th International Conference on Machine Learning (ICML-03)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"key":"ref12","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Advances in Neural Information Processing Svstems"},{"key":"ref13","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems","year":"2016","author":"abadi","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ChiCC.2016.7554262"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3182\/20050703-6-CZ-1902.00243"},{"key":"ref18","article-title":"SA-RL Algorithm Based Ship Steering Controller","volume":"3","author":"ye","year":"2005","journal-title":"Neural Networks and Brain 2005 ICNN & B '05 International Conference on"},{"key":"ref19","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning (ICML-14)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref8","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-57760-4"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref9"}],"event":{"name":"2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","start":{"date-parts":[[2017,11,16]]},"location":"Daegu","end":{"date-parts":[[2017,11,18]]}},"container-title":["2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8124739\/8170342\/08170388.pdf?arnumber=8170388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,7]],"date-time":"2019-10-07T21:31:21Z","timestamp":1570483881000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8170388\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/mfi.2017.8170388","relation":{},"subject":[],"published":{"date-parts":[[2017,11]]}}}