# tianqiraf/DouZero_For_HappyDouDiZhu

基于DouZero定制AI实战欢乐斗地主

Repository: https://github.com/tianqiraf/DouZero_For_HappyDouDiZhu
Canonical: https://ross.abutalabs.com/products/douzero_for_happydoudizhu
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2022-05-28T15:46:52+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1879, "days_push": 1558, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2065, forks 443 (observed 2026-08-28T04:06:10.068108+00:00)

## What it is
A Python desktop application that applies the DouZero reinforcement-learning Dou Dizhu (Chinese card game) AI to the popular Happy DouDiZhu game. It captures the game window, recognizes cards via template matching, and suggests moves in real time through a PyQt interface.

## Use cases
- get AI move suggestions while playing Happy DouDiZhu
- run DouZero models against a live card game
- recognize playing cards from screen captures
- experiment with reinforcement learning game agents in practice
- adjust screen coordinates for pixel-level card detection
- compare SL, DouZero-WP, and DouZero-ADP pretrained models

## When to choose
- you want to use DouZero AI with the Happy DouDiZhu Windows client
- you need a ready-made screen-recognition card game assistant
- you want to study applying RL models to real game UIs

## When to avoid
- you need a headless or cross-platform solution
- your screen resolution differs significantly from 1920x1080 and you cannot adjust coordinates
- you want a general-purpose card game engine rather than a game-specific assistant

## Facets
- artifact type: application
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing, gui
- domain: artificial-intelligence, machine-learning, gaming-tools, computer-vision
- platform: windows, python
- tags: douzero, doudizhu, card-game-ai, screen-recognition, pyqt, reinforcement-learning, game-assistant, desktop

## Member repositories
- tianqiraf/DouZero_For_HappyDouDiZhu (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:10.068108+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:56:57.889470+00:00, confidence not recorded.
  - readme: https://github.com/tianqiraf/DouZero_For_HappyDouDiZhu (fetched 2026-08-28T04:06:10.068108+00:00, sha 5ba6349444b7)
- Data as of 2026-08-30T08:39:29.467469+00:00.