Voyager Minecraft Agent
Voyager demonstrates how AI agents can autonomously learn and improve in complex environments without traditional training methods.
Voyager, the first lifelong learning agent for Minecraft, uses GPT-4 to play purely in-context. The agent continuously improves by writing, refining, and retrieving code from a skill library. Voyager obtains 3.3× more unique items, travels 2.3× longer distances, and unlocks tech tree milestones 15.3× faster than prior methods. The project is fully open-source with code available on GitHub.
还记得三年 GPT-4 玩 Minecraft 吗？那时候还要借助专门的脚本，还要自己做记忆库技能库。 现在 GPT-6 Astra 借助 Computer Use 就可以直接搞定了。 但现在看 Voyager 依然很了不起，那时候就已经实现了 Skill 的自进化和记忆功能，算是最早的 Harness 雏形之一了。 Your browser does not support the video tag. 🔗 View on Twitter Jim Fan @DrJimFan What if we set GPT-4 free in Minecraft? ⛏️ I’m excited to announce Voyager, the first lifelong learning agent that plays Minecraft purely in-context. Voyager continuously improves itself by writing, refining, committing, and retrieving *code* from a skill library. GPT-4 unlocks a new paradigm: “training” is code execution rather than gradient descent. “Trained model” is a codebase of skills that Voyager iteratively composes, rather than matrices of floats. We are pushing no-gradient architecture to its limit. Voyager rapidly becomes a seasoned explorer. In Minecraft, it obtains 3.3× more unique items, travels 2.3× longer distances, and unlocks key tech tree milestones up to 15.3× faster than prior methods. We open-source everything. Let generalist agents emerge in Minecraft! Welcome you all to try today: voyager.minedojo.org Paper: arxiv.org/abs/2305.16291 Code: github.com/MineDojo/Voyag… Deep dive with me: 🧵 Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 5 👀 2229 📊 1 ⚡
