{"id":43804,"date":"2026-11-13T10:59:29","date_gmt":"2026-11-13T10:59:29","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/optimizing-warehouse-logistics-task-driven-reinforcement-learning-with-multi-agent-queuing\/"},"modified":"2026-11-13T10:59:29","modified_gmt":"2026-11-13T10:59:29","slug":"optimizing-warehouse-logistics-task-driven-reinforcement-learning-with-multi-agent-queuing","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/optimizing-warehouse-logistics-task-driven-reinforcement-learning-with-multi-agent-queuing\/","title":{"rendered":"Optimizing Warehouse Logistics: Task-Driven Reinforcement Learning with Multi-Agent Queuing"},"content":{"rendered":"<p>Current manufacturing trends indicate a growing demand for highly customizable production environments, increasing the need for flexible supply chains and automated logistics processes. Warehouses, and particularly order picking, play a crucial role in supply chain productivity. Automated guided vehicles ({AGVs}) are nowadays used to automate the picking process, requiring efficient solutions to the multi-agent pickup and delivery ({MAPD}) problem. {MAPD} involves the assignment of transport orders to vehicles and the planning of conflictfree paths, which can be addressed either jointly (coupled) or separately (decoupled). While coupled approaches yield higherquality solutions, decoupled approaches are less complex but require a trade-off between scalability and solution quality. In this paper, we present task-driven attention decoupled reinforcement learning ({TAD}-{RL}). We evaluate {TAD}-{RL} against several well-known traditional decoupled {MAPD} algorithms within a custom simulation environment. Results show that reinforcement learning is advantageous in scenarios where high traffic volumes cause significant delays, computing efficient task assignments even with 1,000 {AGVs}.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Current manufacturing trends indicate a growing demand for highly customizable production environments, increasing the need for flexible supply chains and automated logistics processes. Warehouses, and particularly order picking, play a crucial role in supply chain productivity. Automated guided vehicles ({AGVs}) are nowadays used to automate the picking process, requiring efficient solutions to the multi-agent pickup and delivery ({MAPD}) problem. {MAPD} involves the assignment of transport orders to vehicles and the [&hellip;]<\/p>\n","protected":false},"author":14,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[32],"publication-year":[1680],"class_list":["post-43804","publication","type-publication","status-publish","hentry","publication-type-inproceedings","publication-year-1680"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/43804","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/14"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/43804\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=43804"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=43804"},{"taxonomy":"publication-year","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-year?post=43804"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}