Deep Multi-Agent Reinforcement Learning using DNN-Weight Evolution to Optimize Supply Chain Performance
Deep Multi-Agent Reinforcement Learning using DNN-Weight Evolution to Optimize Supply Chain Performance
复制标题
使用 DNN 权重进化的深度多智能体强化学习来优化供应链性能
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
K. Yano
中科院分区：
文献类型：
--
作者：
Taiki Fuji;Kiyoto Ito;K. Matsumoto;K. Yano
为了开发一个供应链管理（SCM）系统，在链中的每个实体和整个链，一个多智能体强化学习（MARL）技术的最佳表现。为了解决供应链管理中MARL的两个问题（为供应链构建马尔可夫决策过程和避免类似于“囚徒困境”的学习停滞），开发了一种具有深度神经网络（DNN）-权重进化（LM-DWE）的学习管理方法。通过使用啤酒分销游戏（BDG）作为一个例子的供应链，四个代理系统进行了实验。因此，LM-DWE成功地解决了上述两个问题，并实现了80.0%的总成本低于专家球员的BDG。
To develop a supply chain management (SCM) system that performs optimally for both each entity in the chain and the entire chain, a multi-agent reinforcement learning (MARL) technique has been developed. To solve two problems of the MARL for SCM (building a Markov decision processes for a supply chain and avoiding learning stagnation in a way similar to the “prisoner’s dilemma”), a learning management method with deep-neural-network (DNN)-weight evolution (LM-DWE) has been developed. By using a beer distribution game (BDG) as an example of a supply chain, experiments with a four-agent system were performed. Consequently, the LM-DWE successfully solved the above two problems and achieved 80.0% lower total cost than expert players of the BDG.