Welcome to XuanCe’s documentation!¶
XuanCe is an open-source ensemble of Deep Reinforcement Learning (DRL) algorithm implementations.
We call it as Xuan-Ce (玄策) in Chinese.
DRL algorithms are sensitive to hyper-parameters tuning, varying in performance with different tricks, and suffering from unstable training processes, therefore, sometimes DRL algorithms seems elusive and “Xuan”. This project gives a thorough, high-quality and easy-to-understand implementation of DRL algorithms, and hope this implementation can give a hint on the magics of reinforcement learning.
We expect it to be compatible with multiple deep learning toolboxes:
PyTorch, TensorFlow, and MindSpore,
and hope it can really become a zoo full of DRL algorithms.
Currently, XuanCe has been open-sourced on GitHub:
Why XuanCe?¶
XuanCe is designed to simplify the implementation and design process of deep reinforcement learning algorithms. It could help researchers interested in deep reinforcement learning to quickly understand and grasp the fundamental principles. This, in turn, facilitates developers in algorithm development and design. It has the following key features.
Highly modularized.
Easy to learn, and easy to install.
Felxible for model combination.
Abundant algorithms with various tasks.
supports bith DRL and MARL tasks.
High compatible for different users. (PyTorch, TensorFlow, MindSpore, CPU, GPU, Linux, Windows, MacOS, etc.)
Fast running speed with vector envrionments.
Good visualization effect with tensorboard or wandb toolbox.
The Framework of XuanCe¶
The overall framework of XuanCe is shown as below.
XuanCe contains four main parts:
Part I: Configs. The configurations of hyper-parameters, environments, models, etc.
Part II: Common tools. Reusable tools that are independent of the choice of DL toolbox.
Part III: Envrionments. The supported simulated environments.
Part IV: Algorithms. The key part to build DRL algorithms.
How to use:
APIs:
Benchmarks