DouZero is a reinforcement learning-based AI for playing DouDizhu, a popular Chinese card game. It focuses on perfecting AI strategies for competitive play using value-based deep RL techniques.

Features

  • Optimized AI agent for DouDizhu using RL
  • Uses deep value-based algorithms to learn winning strategies
  • Implements multi-agent reinforcement learning setups
  • Includes pre-trained models for benchmarking
  • Offers efficient training pipelines for rapid experimentation
  • Designed for game-specific strategy learning and human-level play

Project Samples

Project Activity

See All Activity >

License

Apache License V2.0

Follow DouZero

DouZero Web Site

Other Useful Business Software
Easy-to-use online form builder for every business. Icon
Easy-to-use online form builder for every business.

Create online forms and publish them. Get an email for each response. Collect data.

Easy-to-use online form builder for every business. Create online forms and publish them. Get an email for each response. Collect data. Design professional looking forms with JotForm Online Form Builder. Customize with advanced styling options to match your branding. Speed up and simplify your daily work by automating complex tasks with JotForm’s industry leading features. Securely and easily sell products. Collect subscription fees and donations. Being away from your computer shouldn’t stop you from getting the information you need. No matter where you work, JotForm Mobile Forms lets you collect data offline with powerful forms you can manage from your phone or tablet. Get the full power of JotForm at your fingertips. JotForm PDF Editor automatically turns collected form responses into professional, secure PDF documents that you can share with colleagues and customers. Easily generate custom PDF files online!
Learn More
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of DouZero!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

Python

Related Categories

Python Reinforcement Learning Frameworks

Registered

2025-03-13