深度学习-麻将--- - 强化学习麻将实现

项目说明

Deep Learning Mahjong [机器学习深度学习麻將] 🔴

Mahjong [麻將] 🔴

<div>

![Status]()
![GitHub Issues]()
![GitHub Pull Requests]()
![License]()

</div>

#### Moti &#x1F53B;

Watching my grandma play 麻将 online and I was curious how the NPCs made their decisions.

---

#### Game Play &#x1F53B;
* 3 or 4 player draw-and-discard game with 144 tiles based on Chinese characters and symbols.
* Match open pairs of identical tiles, remove from board, exposing the tiles under them for play.
* 游戏 ends when all pairs of tiles have been removed from the board or no more exposed pairs remaining.
* Players get more realistic experiences and playable content in a 游戏 that in skill, strategy, calculation, and chance.

---

#### Types [Make Configurable] &#x1F534;
* Old Hong Kong / Cantonese 麻将 [DEFAULT MODE]
* Competiti International Standard
* Three-Player Mahjong [3-ka]
* Battle Mahjong [Player NPC]

---

#### 游戏 Tile Count Per Set [Total 144] &#x1F53B;
* Simples [108]
* Dots 36
* Bamboo 36
* Characters 36
* Honors [28]
* Winds - [North, West, South, East] 16
* Dragons - [Red, Green, White] 12
* Bonus [8]
* Flower - [Plum Blossom, Orchid, Chrysanthemum, Bamboo] 4
* Seasons - [Spring, Summer, Autumn, Winter] 4
* Mahjong Combos
* Heavenly Hand [天糊]
* Great Winds [大四喜]
* Great Dragons [大三元]
* All Kongs [十八羅漢]
* All Honor Tiles [字一色]
* Thirteen Orphans [十三幺]
* Nine Gates Hand [九蓮宝燈]
* Self Triplets [四暗刻]
* All in Triplets [對對糊]
* Mixed One Suit [混一色]
* All One Suit [清一色]
* Common Hand [平糊]
* Small Dragons [小三元]
* Small Winds [小四喜]

!Image source Wikipedia

---

Technical Mahjong Game Documentation [技术文档] &#x1F534;

#### Mahjong &#x1F53B;
* ML Algorithms allows game to react and respond more dynamically and in more imaginative ways.
* Deep Neural Network with reinforcement learning implemented.
* Learn from its own 游戏 and top human players ( Supervised Learning) where computations are made for every move or position.

!dsada

---

#### Machine Learning [机器学习] &#x1F53B;

* Non-Player Characters (NPCs)
* Algorithms playing as NPCs (with adjustable difficulties) respond to player’s actions in unique, unexpected ways.
* NPCs are non hard-coded.
* Train NPCs by imitating Top Mahjong Players to learn dynamic mo and actions.
* Natural Language Processing [NLP] to build realistic interactions in con. Key for Battle 麻将 [Player NPC] style.

* Computational Modelling
* Complex 游戏 states modelled such that 游戏 can predict and alter downstream effects:
* Ex1: Team chemistry score calculated based on personalities of each gamer.
* Ex2: Morale of each player’s abilities as 游戏 is played in real-time.

* Game Aesthetics
* Ex: Computer Algorithms used for 麻将 textures and objects to render dynamically as player mo on the board.

---

#### Deep Learning [深度学习] &#x1F53B;

* DL Game Play
* AI will win through intelligence rather than faster mechanicals speed.
* Computers can programatically issue commands instantly whereas humans must physically move a mouse or hit the keyboard.
* Knowledge based hierarchy foundation with Goals, Strategies, Tactics, and Chains.
* Each objecti current 游戏 state and decides which lower le will be best to achieve it.

<p align="center"><img src=" ></p>

* Reinforcement Learning
* Marko process to make decisions in chain of if-then statements.
* Positive or Negati.
* Algorithm will learn what actions will maximize the reward and which to be a.

* Deep Neural Network
* 3 Hidden layers of 120 neutrons.
* 3 Dropout layers to optimize generalization and reduce o.
* Input - State
* Output - related to Mahjong Actions
* Last layer uses Softmax Function to return probabilities.

* Deep Q-Learning
* Q-table matrix that updates Q-table based on the Prediction of Future Mahjong States.
* Q- updated according to the Bellman Equation.

!Deep Q action-value function

---

#### Search Gaming Optimization Algorithm [搜索优化] &#x1F53B;

* Alpha-Beta Prunning
* AI weeds out bad moves.
* “Lookahead” Search Algorithms
* Open World Games
* Typically require thousands of hours of de and artist time to render.
* Become more efficient using ML Path-Finding Algorithms.
* Have the potential to be unlimited in size

---

#### Database [数据库] &#x1F534;

* Optimize game data with databases.
* Pre-Computed Moves for the beginning/end phrases of the 游戏.
* Two Databases
* Opening DB
* Endgame DB

---

References [图书] &#x1F534;

* Shiqi Gao et al. Building a Computer 麻将 Player via Deep Con Neural Networks.
* Open Spiel. A 框架 For Reinforcement Learning in Games.
* Pau Ramon Revilla. Open 源码 multiplayer 麻将
* Rules of Mah-Jongg - Joseph Park Babcock
* Maajh: The American of the Ancient Chinese 游戏 - Viola L. Cecil
* The Complete Book of Mah-jongg - Alan D. Millington

技术栈

开发语言：TypeScript

项目类型：强化学习麻将实现

Star 数：101

功能特点

这是一套强化学习麻将实现，代码结构清晰，适合开发者学习游戏的客户端渲染、服务端逻辑、场景管理与资源加载。项目涵盖了游戏的核心玩法、界面交互、地图与角色系统等模块，对理解游戏开发的完整流程具有较高的参考价值。

从技术实现角度看，游戏项目的难点在于：游戏循环与状态管理、资源加载与渲染优化、客户端与服务端的协议同步、以及多平台适配。本项目在这些方面提供了可运行的实现，开发者可以在此基础上进行二次开发或学习研究。

部署说明

1. 下载源码压缩包，解压到本地开发环境。

2. 根据项目类型准备对应的运行环境（Node.js / Go / C# / Unity / Godot 等）。

3. 按照 README 中的步骤配置依赖、数据库和配置文件。

4. 先启动服务端，再运行客户端，即可进入游戏进行测试。

注意：本项目仅供学习研究使用，请勿用于商业或非法用途。

学习价值

对于想进入游戏开发领域的开发者来说，这套源码是一个很好的入门参考。通过阅读代码，可以学习到游戏的核心玩法实现、场景与资源管理、网络协议设计、以及渲染优化等关键技术点。

同时，项目中的代码组织方式和模块划分，也展示了游戏项目在工程化方面的实践经验，值得开发者深入研究和借鉴。理解一个完整游戏项目的架构，对后续开发其他类型游戏也很有帮助。

免责声明

本资源来源于开源社区，仅供学习研究和技术交流使用，请勿用于任何商业或违法违规用途。使用本项目产生的一切后果由使用者自行承担。若涉及第三方权益，请联系删除。