{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T22:15:00Z","timestamp":1780524900971,"version":"3.54.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11323196","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Hierarchical Multi-Agent Deep Reinforcement Learning for Cooperative Exploration of UAV Swarms"],"prefix":"10.1109","author":[{"given":"Nathaniel Mackay","family":"Salt","sequence":"first","affiliation":[{"name":"Durham University,Department of Computer Science,Durham,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farshad","family":"Arvin","sequence":"additional","affiliation":[{"name":"Durham University,Department of Computer Science,Durham,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyan","family":"Hu","sequence":"additional","affiliation":[{"name":"Durham University,Department of Computer Science,Durham,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891991"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3557783"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72062-8_28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3236945"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CAC57257.2022.10055585"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3364356"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801761"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128566"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3239815"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160583"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160565"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/AGENTS.2019.8929192"},{"key":"ref13","author":"Amato","year":"2024","journal-title":"An introduction to centralized training for decentralized execution in cooperative multi-agent reinforcement learning"},{"key":"ref14","author":"Amato","year":"2024","journal-title":"A first introduction to cooperative multi-agent reinforcement learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21094-5_19"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MED54222.2022.9837168"},{"key":"ref17","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC62082.2024.10826729"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1201\/b14581"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref22","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International Conference on Machine Learning","author":"Fujimoto","year":"2018"},{"key":"ref23","first-page":"15032","article-title":"Pettingzoo: Gym for multi-agent reinforcement learning","volume":"34","author":"Terry","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","volume-title":"Multi-Objective Reinforcement Learning","author":"Felten","year":"2024"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11323196.pdf?arnumber=11323196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:38:54Z","timestamp":1768462734000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323196\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323196","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}