Metadata-Version: 2.1
Name: xuance
Version: 1.2.5
Summary: XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library.
Home-page: 
Download-URL: https://github.com/agi-brain/xuance.git
Author: Wenzhang Liu, et al.
Author-email: liu_wzh@foxmail.com
License: MIT
Keywords: deep reinforcement learning,software library,PyTorch,TensorFlow2,MindSpore
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Topic :: Software Development :: Build Tools
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
License-File: LICENSE.txt
Requires-Dist: numpy<1.23.0,>=1.21.6
Requires-Dist: scipy==1.7.3
Requires-Dist: PyYAML
Requires-Dist: gym==0.26.2
Requires-Dist: gymnasium==0.28.1
Requires-Dist: gym-notices==0.0.8
Requires-Dist: pygame>=2.1.0
Requires-Dist: tqdm==4.62.3
Requires-Dist: pyglet==1.5.15
Requires-Dist: pettingzoo>=1.23.0
Requires-Dist: tensorboard>=2.11.2
Requires-Dist: wandb==0.15.3
Requires-Dist: moviepy==1.0.3
Requires-Dist: imageio
Requires-Dist: opencv-python==4.5.4.58
Requires-Dist: mpi4py
Provides-Extra: torch
Requires-Dist: torch==1.13.0; extra == "torch"
Provides-Extra: tensorflow
Requires-Dist: tensorflow==2.6.0; extra == "tensorflow"
Requires-Dist: tensorflow-addons==0.21.0; extra == "tensorflow"
Requires-Dist: tensorflow-probability==0.14.0; extra == "tensorflow"
Provides-Extra: mindspore
Requires-Dist: mindspore==2.2.0; extra == "mindspore"
Provides-Extra: all
Requires-Dist: torch==1.13.0; extra == "all"
Requires-Dist: tensorflow==2.6.0; extra == "all"
Requires-Dist: mindspore==2.2.14; extra == "all"
Provides-Extra: atari
Requires-Dist: gymnasium[accept-rom-license]==0.28.1; extra == "atari"
Requires-Dist: gymnasium[atari]==0.28.1; extra == "atari"
Requires-Dist: ale-py==0.8.1; extra == "atari"
Provides-Extra: box2d
Requires-Dist: swig==4.3.0; extra == "box2d"
Requires-Dist: gymnasium[box2d]==0.28.1; extra == "box2d"
Provides-Extra: minigrid
Requires-Dist: minigrid==3.0.0; extra == "minigrid"
Provides-Extra: metadrive
Requires-Dist: metadrive; extra == "metadrive"
Provides-Extra: rware
Requires-Dist: rware; extra == "rware"

XuanCe is an open-source ensemble of Deep Reinforcement Learning (DRL) algorithm implementations. We call it as Xuan-Ce (玄策) in Chinese. "Xuan (玄)" means incredible and magic box, "Ce (策)" means policy. 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.
