XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library

Wenzhang Liu, Wenzhe Cai, Kun Jiang, Guangran Cheng, Yuanda Wang +5 more
12/25/2023
cs.LGcs.AIcs.DL

Official code: agi-brain/xuance (1,088 stars, MIT, PyTorch, last commit 2026-04-17).

Abstract

In this paper, we present XuanCe, a comprehensive and unified deep reinforcement learning (DRL) library designed to be compatible with PyTorch, TensorFlow, and MindSpore. XuanCe offers a wide range of functionalities, including over 40 classical DRL and multi-agent DRL algorithms, with the flexibility to easily incorporate new algorithms and environments. It is a versatile DRL library that supports CPU, GPU, and Ascend, and can be executed on various operating systems such as Ubuntu, Windows, MacOS, and EulerOS. Extensive benchmarks conducted on popular environments including MuJoCo, Atari, and StarCraftII multi-agent challenge demonstrate the library's impressive performance. XuanCe is open-source and can be accessed at https://github.com/agi-brain/xuance.git.

View on arXivView PDF

Code Implementations(1)

agi-brain/xuanceOfficial100%
PyTorchMIT

XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library

1,088162PythonMay 21, 20236 months agoMIT
a2catariddpgdqngoogle-research-football+14 more

Similar Papers

OpenRL: A Unified Reinforcement Learning Framework

88% match1 repo8382023

RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control

85% match1 repo1.0k2023

A Hierarchical Approach to Population Training for Human-AI Collaboration

85% match2023

MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments

85% match2026

Enhancing the MADDPG Algorithm for Multi-Agent Learning via Action Inference and Importance Sampling

85% match2026

The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Research

85% match1 repo992023

Cite this paper

@article{liu2023xuance,
  title  = {XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library},
  author = {Wenzhang Liu and Wenzhe Cai and Kun Jiang and Guangran Cheng and Yuanda Wang and Jiawei Wang and Jingyu Cao and Lele Xu and Chaoxu Mu and Changyin Sun},
  year   = {2023},
  eprint = {2312.16248},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.16248v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.16248.svg)](https://codeofpaper.com/paper/2312.16248)

Discussion