Open Dreamer 是一个基于 JAX/Flax 的开源、实时 Dreamer 4 世界模型实现,提供了因果视频分词器和以动作为条件的潜在动力学模型的训练代码,适用于 Minecraft/VPT 风格的游戏数据。

Stars

302

7 天增长

暂无数据

Fork 数

24

开放 Issue

1

开源协议

NOASSERTION

最近更新

2026-07-26

AI 仓库情报摘要
FR-AI / ANALYSIS

为什么值得关注

该仓库提供了完整的、可用于生产的 Dreamer 4 训练流程,并附有令人印象深刻的实时浏览器演示,让你可以实时体验生成的 Minecraft 世界,使先进的世界建模对实践者更加友好。

适合谁使用

  • 世界模型和基于模型的强化学习研究人员
  • 使用 JAX/Flax 进行视频生成的深度学习工程师
  • 对 Minecraft 模拟感兴趣的游戏 AI 爱好者
  • 构建交互式神经环境的开发者

典型使用场景

  • 在 Minecraft 视频数据集上训练世界模型,以根据动作预测未来帧
  • 生成实时交互的游戏环境 rollout,用于智能体训练或可视化
  • 使用 Fréchet Video Distance (FVD) 评估视频预测质量
  • 在开放框架中复现并扩展 Dreamer 4 研究成果

项目优势

  • 提供了从原始 Minecraft MP4 数据到分词器和动力学模型的完整训练流程,并配有详细的 Hydra 配置
  • 包含由 Reactor 驱动的实时浏览器演示,无需搭建即可体验世界模型推理
  • 利用 JAX 实现高性能和 GPU 加速,依赖和工作流文档清晰
  • 模块化代码,包括分词器训练、数据集分词、动力学训练和评估 (FVD) 的独立脚本

使用前须知

  • 需要特定格式的 Minecraft/VPT 风格 ArrayRecord 数据,限制了直接应用于其他领域
  • 路线图表明完整的 Dreamer 4 行为克隆/强化学习智能体训练尚未实现
  • 当前采用“保留所有权利”的临时许可,在添加正式开源许可前可能阻碍开源采用

README 快速开始

An open, real-time implementation of the Dreamer 4 world-model pipeline in JAX/Flax.

🌐 Website & Blog Post  ·  🎮 Live Demo  ·  ⚡ Inference Code

Authors

Diego Marti Monso*  ·  Francesco Sacco*  ·  Edward Hu

  • Equal contribution

REAL-TIME DEMO POWERED BY


Open Dreamer is a simple, performant, and easy-to-use JAX/Flax NNX implementation of the Dreamer 4 world model — trained on Minecraft/VPT-style gameplay and playable in real time. This repository holds the training pipeline: a causal video tokenizer, an action-conditioned latent dynamics model, and the tools to generate rollouts and measure quality.

This repo currently supports:

  • Training a causal video tokenizer
  • Tokenizing Minecraft/VPT-style MP4 datasets
  • Training an action-conditioned latent dynamics model
  • Generating rollouts and computing FVD

🎮 Try it now

The fastest way to experience Open Dreamer is the live, in-browser demo — step into a generated Minecraft world and play it in real time, with a Game ⟷ Dream toggle that hands the stream from the real game to the world model frame by frame. No setup required; the real-time model runs in the cloud on Reactor.

👉 Open the demo

The website also walks through how the model works, with interactive figures and result galleries.

⚡ Run it yourself

To roll out the trained model locally on your own video and actions — generating new frames from an MP4 and a matching action sequence — use the inference repository:

👉 reactor-team/open-dreamer

The rest of this README covers training the model from scratch.

📋 Roadmap

  • Full Dreamer 4 Behaviour-Cloning / RL agent training loop

⚙️ Requirements

Install

pip install uv
uv sync
source .venv/bin/activate

The dependency lock targets CUDA 12 JAX. If your machine needs a different JAX build, in

项目描述

Open-source Dreamer world-model implementation in JAX

相关仓库与替代方案

根据分类、Topic 和编程语言匹配的相似项目。

lopopolo
精选
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI 与机器学习AI 智能体
2,390
slvDev
精选
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI 与机器学习大语言模型
1,960
littledivy
精选
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI 与机器学习
1,482