{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:18:27Z","timestamp":1761895107437,"version":"build-2065373602"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210182","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Action Decomposition-based Actor-Critic for Supply Chain Optimization"],"prefix":"10.1109","author":[{"given":"Zhengrong","family":"Chen","sequence":"first","affiliation":[{"name":"Guangdong University of Technology,School of Comp. Sci. & Tech.,Guangzhou,China"}]},{"given":"Qinghua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Comp. Sci. & Tech.,Guangzhou,China"}]},{"given":"An","family":"Zeng","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Comp. Sci. & Tech.,Guangzhou,China"}]},{"given":"YuZhu","family":"Ji","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Comp. Sci. & Tech.,Guangzhou,China"}]},{"given":"Baoyao","family":"Yang","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Comp. Sci. & Tech.,Guangzhou,China"}]},{"given":"Dan","family":"Pan","sequence":"additional","affiliation":[{"name":"Guangdong Polytechnic Normal University,School of Elec. & Info.,Guangzhou,China"}]}],"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":"10.1016\/j.compchemeng.2015.03.015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/opre.40.4.808"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2140221"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1287\/msom.2021.1064"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/pr9010102"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2024.2311180"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2023.109088"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2023.109099"},{"key":"ref10","first-page":"23609","article-title":"A hierarchical reinforcement learning based optimization framework for large-scale dynamic pickup and delivery problems","volume":"34","author":"Ma","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref12","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":"ref13","first-page":"4045","article-title":"Time limits in reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Pardo"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"article-title":"D2rl: Deep dense architectures in reinforcement learning","year":"2020","author":"Sinha","key":"ref15"},{"article-title":"Asynchronous methods for deep reinforcement learning","year":"2016","author":"Mnih","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref18","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref19"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210182.pdf?arnumber=11210182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:43:11Z","timestamp":1761889391000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210182","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}