A generally applicable implementation of the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm across most reinforcement learning environments
大部分强化学习环境通用的MADDPG算法实现
This version of the MADDPG implementation references Phil's version. Here is Phil's YouTube channel@Machine Learning with Phil, thanks to Phil!
此版本的MADDPG实现参考了Phil的版本,这是Phil的Youtube频道@Machine Learning with Phil,感谢Phil!
Welcome to visit my Github Pages
欢迎访问我的GithubPages
The neural network architecture in this version is arbitrarily designed, and users need to customize the network layers according to their specific reinforcement learning tasks
此版本的神经网络只是随意设计的,用户需要根据自己的强化学习任务自定义网络层