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: https://voyager.minedojo.org
Code: https://github.com/MineDojo/Voyager Deep dive with me:
Generally capable, autonomous agents are the next frontier of AI. They continuously explore, plan, and develop new skills in open-ended worlds, driven by survival & curiosity. Minecraft is by far the best testbed with endless possibilities for agents:GPT3 is powerful but blind. The future of Foundation Models will be embodied agents that proactively take actions, endlessly explore the world, and continuously self-improve. What does it take? In our NeurIPS Outstanding Paper “MineDojo”, we provide a blueprint for this future:
Voyager has 3 key components: 1) An iterative prompting mechanism that incorporates game feedback, execution errors, and self-verification to refine programs;
2) A skill library of code to store & retrieve complex behaviors;
3) An automatic curriculum to maximize exploration.
3:15 PM · May 26, 2023