{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T22:31:55Z","timestamp":1768516315579,"version":"3.49.0"},"reference-count":31,"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\/icpads67057.2025.11323034","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":0,"title":["Decentralized Reinforcement Learning for Cooperative Multi-Robot Navigation"],"prefix":"10.1109","author":[{"given":"Yihao","family":"Zheng","sequence":"first","affiliation":[{"name":"Durham University,Department of Computer Science,Durham,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farshad","family":"Arvin","sequence":"additional","affiliation":[{"name":"Durham University,Department of Computer Science,Durham,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyan","family":"Hu","sequence":"additional","affiliation":[{"name":"Durham University,Department of Computer Science,Durham,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3557783"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2024.101491"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT63637.2025.10965305"},{"issue":"1","key":"ref4","first-page":"9","article-title":"Coordinating hundreds of cooperative, autonomous vehicles in warehouses","volume":"29","author":"Wurman","year":"2008","journal-title":"AI Magazine"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111121"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631084"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3233\/978-1-61499-672-9-810"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017643"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref11","author":"Mnih","year":"2013","journal-title":"Playing Atari with Deep Reinforcement Learning"},{"key":"ref12","author":"Schulman","year":"2017","journal-title":"Proximal Policy Optimization Algorithms"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342305"},{"key":"ref14","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016","journal-title":"PmLR"},{"key":"ref15","author":"Haarnoja","year":"2019","journal-title":"Soft ActorCritic Algorithms and Applications"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17466"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3139145"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3292004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801914"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/socs.v10i1.18510"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341668"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3077863"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560748"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","first-page":"7487","article-title":"Stabilizing Transformers for Reinforcement Learning","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Parisotto"},{"key":"ref28","author":"Wang","year":"2016","journal-title":"Dueling Network Architectures for Deep Reinforcement Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11631"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"}],"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\/11323034.pdf?arnumber=11323034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:42:10Z","timestamp":1768462930000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323034\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323034","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}