原创Multi-Agent Reinforcement Learning基本概念&三种架构
参考内容在References写出，仅作为个人学习笔记，如有错误欢迎指出。References的一本偏向数学推理的DRL新书即将上线？安排上Multi-Agent Reinforcement Learning基本概念(1/2)SettingsFully cooperative 相互配合 e.g. 工业机器人Fully competitive 一方的收益是另一方的损失（捕猎者和猎物），如 零和博弈，
Stay hungry. Stay foolish.
原创[PaperNotes]2020.Optimizing Federated Learning on Non-IID Data with Reinforcement Learning
Optimizing Federated Learning on Non-IID Data with Reinforcement Learning文章链接：https://ieeexplore.ieee.org/document/9155494/作者：Hao Wang，Zakhary Kaplan，Di Niu，Baochun Li发表：IEEE INFOCOM 2020 - IEEE Confe
原创[MIT 6.824]Labs's Notes
MIT 6.824 labs's notes
