
DQN_WUKONG
基于强化学习的黑神话悟空AI
Stars: 62

DQN_WUKONG is a repository containing code for training an AI model to play a specific game. It provides instructions for setting up the environment using Conda or venv, as well as details on key files such as window.py, judge.py, restart.py, and main.py. The repository includes scripts for training the model and specific configurations for gameplay. It also references a BossRush V3 mod for repetitive training and acknowledges code contributions from other repositories like DQN_play_sekiro and pygta5. For a more general AI framework, users can refer to the GameAISDK repository.
README:
https://www.bilibili.com/video/BV1DrpheREXh
conda create --name wukong python=3.10
conda activate wukong
为了避免兼容性问题,你可以先使用 Conda 安装一些比较常见的库,再通过 pip
安装其余库:
# 使用 Conda 安装主要库
conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
# 使用 pip 安装其余库
pip install --upgrade pip
pip install -r requirements.txt
安装完成后,确认所有库是否正确安装:
python -c "import torch; print(f'PyTorch version: {torch.__version__}'); print('GPU is', 'available' if torch.cuda.is_available() else 'not available')"
python -m venv .venv
# windows 运行activate 激活环境
\.venv\Scripts\activate.bat
# 安装依赖
pip install -r requirements.txt
- window.py:画面各血条的矩形坐标定义
- judge.py: 奖励分计算
- restart.py: 死亡后从土地庙自动走到boss的固定逻辑
- main.py: 程序入口
游戏设置:显示模式修改为窗口模式,分辨率调整为1280*720,你也可以在window.py中调整自己喜欢的窗口分辨率 游戏窗口需要以左上角为起始坐标,我们已经在你启动display_game_info.py脚本的时候做了这个事情
# 实际游戏窗口大小
game_width = 1280 # NOTE: 替换成你游戏的宽度和分辨率
game_height = 720
修改好分辨率后,运行下面的脚本,查看血量识别这些是否吻合
python -m utils.display_game_info
修改合适的死亡自动寻路脚本 restart 死亡自动训练逻辑后面改成了由config.yaml配置控制,你可在actions_config.yaml中配置动作进行死亡寻路自动训练
或者改回原先的restart脚本方式
启动脚本训练,根据提示按g可暂停和开始,启动脚本后,需要进入boss对战看到boss血条后,等待几秒即可启动模型。
python main.py
作者演示视频: https://www.bilibili.com/video/BV1QDxHeBETk N站下载链接:https://www.nexusmods.com/blackmythwukong/mods/668
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for DQN_WUKONG
Similar Open Source Tools

DQN_WUKONG
DQN_WUKONG is a repository containing code for training an AI model to play a specific game. It provides instructions for setting up the environment using Conda or venv, as well as details on key files such as window.py, judge.py, restart.py, and main.py. The repository includes scripts for training the model and specific configurations for gameplay. It also references a BossRush V3 mod for repetitive training and acknowledges code contributions from other repositories like DQN_play_sekiro and pygta5. For a more general AI framework, users can refer to the GameAISDK repository.

mediasoup-client-aiortc
mediasoup-client-aiortc is a handler for the aiortc Python library, allowing Node.js applications to connect to a mediasoup server using WebRTC for real-time audio, video, and DataChannel communication. It facilitates the creation of Worker instances to manage Python subprocesses, obtain audio/video tracks, and create mediasoup-client handlers. The tool supports features like getUserMedia, handlerFactory creation, and event handling for subprocess closure and unexpected termination. It provides custom classes for media stream and track constraints, enabling diverse audio/video sources like devices, files, or URLs. The tool enhances WebRTC capabilities in Node.js applications through seamless Python subprocess communication.

rag-chatbot
rag-chatbot is a tool that allows users to chat with multiple PDFs using Ollama and LlamaIndex. It provides an easy setup for running on local machines or Kaggle notebooks. Users can leverage models from Huggingface and Ollama, process multiple PDF inputs, and chat in multiple languages. The tool offers a simple UI with Gradio, supporting chat with history and QA modes. Setup instructions are provided for both Kaggle and local environments, including installation steps for Docker, Ollama, Ngrok, and the rag_chatbot package. Users can run the tool locally and access it via a web interface. Future enhancements include adding evaluation, better embedding models, knowledge graph support, improved document processing, MLX model integration, and Corrective RAG.

photo-ai
100xPhoto is a powerful AI image platform that enables users to generate stunning images and train custom AI models. It provides an intuitive interface for creating unique AI-generated artwork and training personalized models on image datasets. The platform is built with cutting-edge technology and offers robust capabilities for AI image generation and model training.

gpt-bitcoin
The gpt-bitcoin repository is focused on creating an automated trading system for Bitcoin using GPT AI technology. It provides different versions of trading strategies utilizing various data sources such as OHLCV, Moving Averages, RSI, Stochastic Oscillator, MACD, Bollinger Bands, Orderbook Data, news data, fear/greed index, and chart images. Users can set up the system by creating a .env file with necessary API keys and installing required dependencies. The repository also includes instructions for setting up the environment on local machines and AWS EC2 Ubuntu servers. The future plan includes expanding the system to support other cryptocurrency exchanges like Bithumb, Binance, Coinbase, OKX, and Bybit.

100x-LLM
This repository contains code snippets and examples from the 100x Applied AI cohort lectures. It includes implementations of LLM Workflows, RAG (Retrieval Augmented Generation), Agentic Patterns, Chat Completions with various providers, Function Calling, and more. The repository structure consists of core components like LLM Workflows, RAG Implementations, Agentic Patterns, Chat Completions, Function Calling, Hugging Face Integration, and additional components for various agent implementations, presentation generation, Notion API integration, FastAPI-based endpoints, authentication implementations, and LangChain usage examples.

aicommit2
AICommit2 is a Reactive CLI tool that streamlines interactions with various AI providers such as OpenAI, Anthropic Claude, Gemini, Mistral AI, Cohere, and unofficial providers like Huggingface and Clova X. Users can request multiple AI simultaneously to generate git commit messages without waiting for all AI responses. The tool runs 'git diff' to grab code changes, sends them to configured AI, and returns the AI-generated commit message. Users can set API keys or Cookies for different providers and configure options like locale, generate number of messages, commit type, proxy, timeout, max-length, and more. AICommit2 can be used both locally with Ollama and remotely with supported providers, offering flexibility and efficiency in generating commit messages.

TalkWithGemini
Talk With Gemini is a web application that allows users to deploy their private Gemini application for free with one click. It supports Gemini Pro and Gemini Pro Vision models. The application features talk mode for direct communication with Gemini, visual recognition for understanding picture content, full Markdown support, automatic compression of chat records, privacy and security with local data storage, well-designed UI with responsive design, fast loading speed, and multi-language support. The tool is designed to be user-friendly and versatile for various deployment options and language preferences.

ruby-nano-bots
Ruby Nano Bots is an implementation of the Nano Bots specification supporting various AI providers like Cohere Command, Google Gemini, Maritaca AI MariTalk, Mistral AI, Ollama, OpenAI ChatGPT, and others. It allows calling tools (functions) and provides a helpful assistant for interacting with AI language models. The tool can be used both from the command line and as a library in Ruby projects, offering features like REPL, debugging, and encryption for data privacy.

lite_llama
lite_llama is a llama model inference lite framework by triton. It offers accelerated inference for llama3, Qwen2.5, and Llava1.5 models with up to 4x speedup compared to transformers. The framework supports top-p sampling, stream output, GQA, and cuda graph optimizations. It also provides efficient dynamic management for kv cache, operator fusion, and custom operators like rmsnorm, rope, softmax, and element-wise multiplication using triton kernels.

one
ONE is a modern web and AI agent development toolkit that empowers developers to build AI-powered applications with high performance, beautiful UI, AI integration, responsive design, type safety, and great developer experience. It is perfect for building modern web applications, from simple landing pages to complex AI-powered platforms.

echo-editor
Echo Editor is a modern AI-powered WYSIWYG rich-text editor for Vue, featuring a beautiful UI with shadcn-vue components. It provides AI-powered writing assistance, Markdown support with real-time preview, rich text formatting, tables, code blocks, custom font sizes and styles, Word document import, I18n support, extensible architecture for creating extensions, TypeScript and Tailwind CSS support. The tool aims to enhance the writing experience by combining advanced features with user-friendly design.

AI-Agent-Starter-Kit
AI Agent Starter Kit is a modern full-stack AI-enabled template using Next.js for frontend and Express.js for backend, with Telegram and OpenAI integrations. It offers AI-assisted development, smart environment variable setup assistance, intelligent error resolution, context-aware code completion, and built-in debugging helpers. The kit provides a structured environment for developers to interact with AI tools seamlessly, enhancing the development process and productivity.

ai-commits-intellij-plugin
AI Commits is a plugin for IntelliJ-based IDEs and Android Studio that generates commit messages using git diff and OpenAI. It offers features such as generating commit messages from diff using OpenAI API, computing diff only from selected files and lines in the commit dialog, creating custom prompts for commit message generation, using predefined variables and hints to customize prompts, choosing any of the models available in OpenAI API, setting OpenAI network proxy, and setting custom OpenAI compatible API endpoint.
For similar tasks

DQN_WUKONG
DQN_WUKONG is a repository containing code for training an AI model to play a specific game. It provides instructions for setting up the environment using Conda or venv, as well as details on key files such as window.py, judge.py, restart.py, and main.py. The repository includes scripts for training the model and specific configurations for gameplay. It also references a BossRush V3 mod for repetitive training and acknowledges code contributions from other repositories like DQN_play_sekiro and pygta5. For a more general AI framework, users can refer to the GameAISDK repository.

openkore
OpenKore is a custom client and intelligent automated assistant for Ragnarok Online. It is a free, open source, and cross-platform program (Linux, Windows, and MacOS are supported). To run OpenKore, you need to download and extract it or clone the repository using Git. Configure OpenKore according to the documentation and run openkore.pl to start. The tool provides a FAQ section for troubleshooting, guidelines for reporting issues, and information about botting status on official servers. OpenKore is developed by a global team, and contributions are welcome through pull requests. Various community resources are available for support and communication. Users are advised to comply with the GNU General Public License when using and distributing the software.

Top-Osu-Hacks-2024-Aim-Assist-Bots-and-More
The Top-Osu!-Hacks-2024 repository is a comprehensive collection of cheats and mods designed to enhance gameplay experience in Osu!. It offers aim assist, relax hacks, undetected bots, and various cheats to improve gameplay. Users can easily download and install these hacks to automate gameplay, improve aim, and enjoy the game with relaxed settings. The repository is optimized for search engines and provides the latest and most effective hacks for Osu! in 2024.

THE-SANDBOX-AutoClicker
The Sandbox AutoClicker is a bot designed for the crypto game The Sandbox, allowing users to automate various processes within the game. The tool offers features such as auto tuning, multi-account auto clicker, multi-threading, a convenient menu, and free proxies. It provides full optimization through a simple menu and is guaranteed to be safe for Windows systems, supporting versions 7/8/8.1/10/11 (x32/64).

momoai-AutoClicker
momoai-AutoClicker is a bot designed for the crypto game MomoAI, allowing users to automate various processes within the game. The tool offers features such as auto tuning, auto clicker for multiple accounts, multi-threading capabilities, a convenient menu, and free proxies. It provides full optimization through a simple menu interface and ensures the safety of the Windows system. Compatible with Windows 7/8/8.1/10/11 (x32/64).

Top-Osu-Hacks-2024-Aim-Assist-Bots-and-Mor
The Top-Osu!-Hacks-2024 repository offers a comprehensive suite of powerful cheats and mods designed to enhance gameplay experience in Osu!. It provides aim assist hacks, bots, and various cheats to improve gameplay. Users can easily download and install the cheats to automate gameplay, improve aim accuracy, and play with relaxed settings. The repository is optimized for search engines using targeted keywords and meta descriptions to help players find Osu! hacks easily.

OpenCAGE
OpenCAGE is an open-source modding toolkit for Alien: Isolation, enabling custom scripting, configuration, and content modification through graphical interfaces. It includes tools for editing assets, configurations, scripts, behaviour trees, launching the game, and managing backups. The project is constantly evolving with a roadmap that includes features like contextual script editing, content porter, new level creator, mod installers, 3D viewer improvements, navmesh generation, skinned meshes support, sound import/export, and more. OpenCAGE is supported financially by the community and welcomes code contributions.

rust-snake-ai-ratatui
This repository contains an AI implementation that learns to play the classic game Snake in the terminal. The AI is built using Rust and Ratatui. Users can clone the repo, run the simulation, and configure various settings to customize the AI's behavior. The project also provides options for minimal UI, training custom networks, and watching the AI complete the game on different board sizes. The developer shares updates and insights about the project on Twitter and plans to create a detailed blog post explaining the AI's workings.
For similar jobs

sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.