{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:46:50Z","timestamp":1770846410298,"version":"3.50.1"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342630","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"1211-1218","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Agent Reinforcement Learning Algorithm Using Dynamic OW-QMIX in Complex Supply Chain Scenarios"],"prefix":"10.1109","author":[{"given":"Zhiqi","family":"Liu","sequence":"first","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006"}]},{"given":"Qinghua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006"}]},{"given":"An","family":"Zeng","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006"}]},{"given":"Yuzhu","family":"Ji","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006"}]},{"given":"Baoyao","family":"Yang","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China,510006"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/j.2158-1592.2001.tb00001.x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/opre.40.4.808"},{"key":"ref3","first-page":"218","article-title":"Multi-model change control of supply chain systems based on digital twin in complex environments","volume-title":"Proceedings of the 2024 International Conference on Automation and Instrumentation (ICAIS)","author":"Meng"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/s24237461"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISPCEM60569.2023.00129"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2020.103239"},{"key":"ref7","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/fi16050163"},{"key":"ref9","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/24725854.2023.2217248"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2023.109099"},{"key":"ref12","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International conference on machine learning","author":"Silver"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/asmb.2723"},{"key":"ref14","first-page":"10 199","article-title":"Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"178","key":"ref15","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref16","first-page":"4045","article-title":"Time limits in reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Pardo"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CAC53003.2021.9728241"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.10.042"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342630.pdf?arnumber=11342630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:53:23Z","timestamp":1770843203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342630\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342630","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}