{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T05:17:07Z","timestamp":1737004627251,"version":"3.33.0"},"reference-count":9,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government [MSIT (Ministry of Science and ICT (Information and Communications Technology))]","doi-asserted-by":"publisher","award":["RS-2024-00439803"],"award-info":[{"award-number":["RS-2024-00439803"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,16]]},"DOI":"10.1109\/ictc62082.2024.10827111","type":"proceedings-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:40:10Z","timestamp":1736883610000},"page":"1163-1165","source":"Crossref","is-referenced-by-count":0,"title":["Introduction to Reinforcement Learning for Torpedo Guidance with Obstacle Avoidance"],"prefix":"10.1109","author":[{"given":"Hyunsoo","family":"Lee","sequence":"first","affiliation":[{"name":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"}]},{"given":"Joongheon","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3143175"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3190379"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2933417"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3346917"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20732"},{"key":"ref6","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. International Conference on Machine Learning (ICML)","volume":"48","author":"Mnih"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3366252"},{"key":"ref8","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th International Conference on Learning Representations (ICLR)","author":"Lillicrap","key":"ref9"}],"event":{"name":"2024 15th International Conference on Information and Communication Technology Convergence (ICTC)","start":{"date-parts":[[2024,10,16]]},"location":"Jeju Island, Korea, Republic of","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 15th International Conference on Information and Communication Technology Convergence (ICTC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10826571\/10826594\/10827111.pdf?arnumber=10827111","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T07:03:03Z","timestamp":1736924583000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10827111\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":9,"URL":"https:\/\/doi.org\/10.1109\/ictc62082.2024.10827111","relation":{},"subject":[],"published":{"date-parts":[[2024,10,16]]}}}