{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:20:47Z","timestamp":1769746847168,"version":"3.49.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3563906","type":"journal-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T17:06:45Z","timestamp":1745514405000},"page":"72938-72952","source":"Crossref","is-referenced-by-count":1,"title":["Wake Homing Torpedo Guidance Using a Hierarchical Deep Reinforcement Learning Framework"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8594-629X","authenticated-orcid":false,"given":"Kunchul","family":"Hwang","sequence":"first","affiliation":[{"name":"Robotics Program, KAIST, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6886-2449","authenticated-orcid":false,"given":"Jinwhan","family":"Kim","sequence":"additional","affiliation":[{"name":"Robotics Program, KAIST, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"4","key":"ref1","first-page":"1","article-title":"Modern torpedoes and countermeasures","volume":"3","author":"Austin","year":"2001","journal-title":"Bharat Rakshak Monitor"},{"key":"ref2","first-page":"123","article-title":"Start worrying about wake homing torpedoes","author":"Friedman","year":"1994"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2012.2192344"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANS.2007.4449232"},{"key":"ref5","article-title":"Cavitation effects on a ship-like box structure subjected to an underwater explosion","author":"Woood","year":"1998"},{"key":"ref6","volume-title":"Decoy device against wake-tracking torpedoes","author":"Guelou","year":"2005"},{"key":"ref7","first-page":"190","article-title":"A guidance logic development for wake homing guidance system","volume-title":"Proc. ICCAS","author":"Kim"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCC.2011.6061712"},{"issue":"4","key":"ref9","first-page":"65","article-title":"The guiding method through keeping distance for the wire and wake guided torpedo","volume":"29","author":"Li","year":"2004","journal-title":"Fire Control Command Control"},{"issue":"3","key":"ref10","first-page":"201","article-title":"Deep reinforcement learning for autonomous underwater vehicle path planning","volume":"15","author":"Chen","year":"2020","journal-title":"J. Underwater Robot. Auton. Syst."},{"issue":"1","key":"ref11","first-page":"55","article-title":"Advanced wake homing strategies for torpedo guidance systems","volume":"132","author":"Davis","year":"2021","journal-title":"Nav. Eng. J."},{"issue":"2","key":"ref12","first-page":"115","article-title":"Simulation and validation of autonomous torpedo guidance algorithms","volume":"28","author":"Rodriguez","year":"2022","journal-title":"Simul. Model. Eng. Sci."},{"key":"ref13","article-title":"Countermeasure anti-torpedo (CAT) warhead subsystem","author":"Goedert","year":"2015"},{"key":"ref14","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2514\/6.2012-4470"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2020.105746"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app10186567"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/1687814018782345"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.9766\/KIMST.2021.24.1.022"},{"key":"ref20","first-page":"1","article-title":"Measuring and modeling bubbles in ship wakes, and their effect on acoustic propagation","volume-title":"Proc. 2nd Int. Conf. Underwater Acoust. Meas., Technol. Results","author":"Culver"},{"key":"ref21","volume-title":"US Navy Insane Drift Technique to Dodge Enemy Torpedoes"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5711\/1082598319219"},{"key":"ref23","article-title":"A study of the motion and stability of torpedoes in 3 degrees of freedom","author":"Leeuwen","year":"1984"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.9709\/JKSS.2014.23.2.007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref26","first-page":"1043","article-title":"Reinforcement learning with hierarchies of machines","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"10","author":"Parr"},{"key":"ref27","first-page":"108","article-title":"Modularity in nervous systems\u2014A key to efficient adaptivity for deep reinforcement learning","volume":"160","author":"Schling","year":"2023","journal-title":"Neural Netw."},{"key":"ref28","first-page":"1","article-title":"HIRO: Hierarchical reinforcement learning with off-policy correction","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Lazarow"},{"issue":"1","key":"ref29","first-page":"1","article-title":"FeUdal networks: Hierarchical reinforcement learning with feudal structure","volume":"20","author":"Pachitariu","year":"2019","journal-title":"J. Mach. Learn. Res."},{"issue":"9","key":"ref30","first-page":"1305","article-title":"HAC: Hierarchical actor-critic","volume":"31","author":"Hausknecht","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref31","first-page":"1","article-title":"MLSH: Multi-level subgoal hierarchies for hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Artif. Intell. (ICAI)","author":"De Souza"},{"issue":"4","key":"ref32","first-page":"310","article-title":"LAHRL: Language as an abstraction for hierarchical deep reinforcement learning","volume":"12","author":"Wang","year":"2022","journal-title":"IEEE Trans. Cogn. Developmental Syst."},{"issue":"8","key":"ref33","first-page":"2345","article-title":"Deep reinforcement learning and the complexity of sub-policy management","volume":"30","author":"Hausknecht","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref34","volume-title":"DEVS: A Formalism for Discrete Event Systems","author":"Zeigler","year":"2000"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18564\/jasss.2871"},{"key":"ref36","article-title":"DEVSIM++ user\u2019s manual","author":"Kim","year":"1994"},{"key":"ref37","first-page":"1","article-title":"Hybrid modeling and simulation methodology based on DEVS formalism","volume-title":"Proc. Summer Computer Simulation Conf.","author":"Barros"},{"key":"ref38","volume-title":"Gym: A Toolkit for Developing and Comparing Reinforcement Learning Algorithms","year":"2016"},{"key":"ref39","first-page":"1","article-title":"Implementation and evaluation of RL algorithms with Q-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Langford"},{"key":"ref40","first-page":"20","article-title":"Modeling and simulating hierarchical models in deep reinforcement learning","volume":"56","author":"Schwienbacher","year":"2022","journal-title":"Simul. Model. Pract. Theory"},{"issue":"1","key":"ref41","first-page":"112","article-title":"Reinforcement learning applied to complex agent systems","volume":"39","author":"Howe","year":"2022","journal-title":"Comput. Intell."},{"issue":"3","key":"ref42","first-page":"144","article-title":"Probabilistic models in reinforcement learning: Theory and application","volume":"22","author":"Kossakowski","year":"2021","journal-title":"J. Artif. Intell."},{"key":"ref43","first-page":"1","article-title":"Reinforcement learning in robotics: Algorithms and applications","volume-title":"Proc. Robotics Conf.","author":"Lee"},{"issue":"4","key":"ref44","first-page":"412","article-title":"A study on reinforcement learning algorithms for multi-agent systems","volume":"37","author":"Siddiqi","year":"2019","journal-title":"J. Auton. Syst."}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10975769.pdf?arnumber=10975769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T17:58:04Z","timestamp":1746467884000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10975769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3563906","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}