{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:52:12Z","timestamp":1781621532273,"version":"3.54.5"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T00:00:00Z","timestamp":1657324800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T00:00:00Z","timestamp":1657324800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,9]]},"DOI":"10.1109\/icarm54641.2022.9959180","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T14:31:50Z","timestamp":1669732310000},"page":"244-249","source":"Crossref","is-referenced-by-count":3,"title":["Safe Multi-Agent Learning Control for Unmanned Surface Vessels Cooperative Interception Mission"],"prefix":"10.1109","author":[{"given":"Bin","family":"Du","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xie","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2011.5986356"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.111453"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.119284"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1061\/AJRUA6.0001199"},{"key":"ref37","author":"schulman","year":"2015","journal-title":"arXiv preprint arXiv 1506 02349"},{"key":"ref36","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2021.110477"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-020-06058-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.110749"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/37.126844","article-title":"Reinforcement learning is direct adaptive optimal control","volume":"12","author":"sutton","year":"1992","journal-title":"IEEE Control Systems Magazine"},{"key":"ref13","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"1","article-title":"Co-design of adaptive event-triggered mechanism and asynchronous h?+? control for 2-d markov jump systems via genetic algorithm","author":"cheng","year":"2022","journal-title":"IEEE Transactions on Cybernetics"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109590"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3112699"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.111507"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3205637"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3189009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17272"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.10.078"},{"key":"ref27","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph17176256"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3074396"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06187-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104476"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.apor.2020.102293"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.110686"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.2966117"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2017.05.009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssci.2022.105955"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref21","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-741252-8.50010-8"},{"key":"ref23","first-page":"1609","article-title":"A convergent o(n) temporal-difference algorithm for off-policy learning with linear function approximation","volume":"21","author":"sutton","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref26","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref25","first-page":"2772","article-title":"Bridging the gap between value and policy based reinforcement learning","volume":"30","author":"nachum","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 International Conference on Advanced Robotics and Mechatronics (ICARM)","location":"Guilin, China","start":{"date-parts":[[2022,7,9]]},"end":{"date-parts":[[2022,7,11]]}},"container-title":["2022 International Conference on Advanced Robotics and Mechatronics (ICARM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9959088\/9959097\/09959180.pdf?arnumber=9959180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T17:35:38Z","timestamp":1760549738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9959180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,9]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icarm54641.2022.9959180","relation":{},"subject":[],"published":{"date-parts":[[2022,7,9]]}}}