{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:58:49Z","timestamp":1759334329960,"version":"build-2065373602"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"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":[[2025,8,17]]},"DOI":"10.1109\/case58245.2025.11164102","type":"proceedings-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:24:07Z","timestamp":1758648247000},"page":"2188-2193","source":"Crossref","is-referenced-by-count":0,"title":["Optimal Multi-agent Reinforcement Learning for Efficient Partially Observable Multi-robot Collaboration in Warehousing"],"prefix":"10.1109","author":[{"given":"Muhammad Naveed","family":"Abbas","sequence":"first","affiliation":[{"name":"Technological University of the Shannon: Midlands Midwest,Software Research Institute,Athlone,Ireland,N37 HD68"}]},{"given":"Paul","family":"Liston","sequence":"additional","affiliation":[{"name":"Technological University of the Shannon: Midlands Midwest,Faculty of Business and Hospitality,Athlone,Ireland,N37 HD68"}]},{"given":"Brian","family":"Lee","sequence":"additional","affiliation":[{"name":"Technological University of the Shannon: Midlands Midwest,Software Research Institute,Athlone,Ireland,N37 HD68"}]},{"given":"Yuansong","family":"Qiao","sequence":"additional","affiliation":[{"name":"Technological University of the Shannon: Midlands Midwest,Software Research Institute,Athlone,Ireland,N37 HD68"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2024.3367237"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/jra.1985.1087002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-5915.1999.tb01619.x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2022.3200138"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802813"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2020.2977374"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112714"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3124466"},{"article-title":"Bench-marking multi-agent deep reinforcement learning algorithms in cooperative tasks","volume-title":"Proc. 35th Conf. Neural Inf. Proc. Syst","author":"Papoudakis","key":"ref9"},{"year":"2022","key":"ref10","article-title":"Guidance automation, Autonomous mobile robots and how they can solve labour shortages"},{"article-title":"A structured self-attentive sentence embedding","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Lin","key":"ref11"},{"article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"Proc. AAAI 2015 Fall Symp. Ser","author":"Hausknecht","key":"ref12"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref13"},{"key":"ref14","first-page":"10 707","article-title":"Shared experience actor-critic for multi-agent reinforcement learning","volume-title":"Proc. 34th Conf. Neural Inf. Proc. Syst","author":"Christianos"},{"issue":"1","key":"ref15","first-page":"9","article-title":"Coordinating hundreds of cooperative, autonomous vehicles in warehouses","volume":"29","author":"Wurman","year":"2008","journal-title":"AI Mag."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2016.08.010"},{"article-title":"Collaborative bots in distribution centers","volume-title":"Proc. 15th IMHRC","author":"Meller","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3837\/tiis.2019.07.013"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tnsm.2021.3093302"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2023.3314395"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3292004"},{"key":"ref25","first-page":"27 840","article-title":"Attention-based recurrence for multi-agent reinforcement learning under stochastic partial observability","volume-title":"Proc. 40th Int. Conf. Mach. Learn","author":"Phan"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2021.3058228"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tgcn.2020.3026453"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2022.3146881"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2023.3288025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"}],"event":{"name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2025,8,17]]},"location":"Los Angeles, CA, USA","end":{"date-parts":[[2025,8,21]]}},"container-title":["2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11163731\/11163732\/11164102.pdf?arnumber=11164102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T14:53:29Z","timestamp":1759244009000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11164102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,17]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/case58245.2025.11164102","relation":{},"subject":[],"published":{"date-parts":[[2025,8,17]]}}}