{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T13:48:37Z","timestamp":1777816117488,"version":"3.51.4"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-20-1-2570"],"award-info":[{"award-number":["N00014-20-1-2570"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-24-1-2522"],"award-info":[{"award-number":["N00014-24-1-2522"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/lra.2024.3518839","type":"journal-article","created":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T19:31:50Z","timestamp":1734377510000},"page":"1194-1201","source":"Crossref","is-referenced-by-count":5,"title":["Distributional Reinforcement Learning Based Integrated Decision Making and Control for Autonomous Surface Vehicles"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0118-7391","authenticated-orcid":false,"given":"Xi","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Stevens Institute of Technology, Hoboken, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3835-5433","authenticated-orcid":false,"given":"Paul","family":"Szenher","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Stevens Institute of Technology, Hoboken, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2505-6022","authenticated-orcid":false,"given":"Yewei","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Stevens Institute of Technology, Hoboken, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7966-2917","authenticated-orcid":false,"given":"Brendan","family":"Englot","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Stevens Institute of Technology, Hoboken, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00773-020-00787-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2019.106436"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3029279"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2013.2254214"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463182"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21900"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/OCEANS40490.2019.8962724"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/14207.001.0001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611668"},{"key":"ref10","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dabney","year":"2018"},{"key":"ref11","article-title":"Distributed distributional deterministic policy gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Barth-Maron","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref13","first-page":"676","article-title":"Sample-based distributional policy gradient","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Singh","year":"2022"},{"key":"ref14","article-title":"COLREGs - International regulations for preventing collisions at sea","volume-title":"Proc. Conv. Int. Regulations Prevent. Collisions Sea","year":"1972"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981226"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2016.10.344"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2801881"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3130386"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2024.3383819"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3022600"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.apor.2021.102759"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.04.008"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/jmse10101431"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/9781119994138"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759050"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref31","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref32","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare","year":"2017"},{"issue":"267","key":"ref33","first-page":"1","article-title":"Tianshou: A highly modularized deep reinforcement learning library","volume":"23","author":"Weng","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","article-title":"Rainbow","author":"Arulkumaran","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/6523158"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10805214\/10804093.pdf?arnumber=10804093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:13:02Z","timestamp":1735197182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10804093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":33,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3518839","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}