Minecraft AI - NVIDIA uses GPT-4 to create a SELF-IMPROVING Autonomous Agent

AI, GPT-4, Minecraft, Nvidia -

Minecraft AI - NVIDIA uses GPT-4 to create a SELF-IMPROVING Autonomous Agent

We introduce VOYAGER, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention.

VOYAGER consists of three key components:

1) an automatic curriculum that maximizes exploration,

2) an ever-growing skill library of executable code for storing and retrieving complex behaviors, and

3) a new iterative prompting mechanism that incorporates environment feedback, execution errors, and self-verification for program improvement. VOYAGER interacts with GPT-4 via blackbox queries, which bypasses the need for model parameter fine-tuning.

The skills developed by VOYAGER are temporally extended, interpretable, and compositional, which compounds the agent’s abilities rapidly and alleviates catastrophic forgetting.

Empirically, VOYAGER shows strong in-context lifelong learning capability and exhibits exceptional proficiency in playing 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 SOTA. VOYAGER is able to utilize the learned skill library in a new Minecraft world to solve novel tasks from scratch, while other techniques struggle to generalize.

 

#minecraft #chatgpt #nvidia

TIMELINE:

[00:00] - Intro

[00:48] - Voyager AI

[01:58] - Minecraft

[02:53] - Mineflayer API

[04:11] - GPT-4

[05:36] - Self-Improving

[07:51] - The Full Prompt Used

[11:18] - The Prompt for Creating Code

[17:58] - GPT-4 Decision Making

[19:00] - The Results

[22:16] - MineDojo (open source)

[23:35] - Implications for coding

 

The Paper: https://arxiv.org/abs/2305.16291


0 comments

Leave a comment

Please note, comments must be approved before they are published

Tags
#WebChat .container iframe{ width: 100%; height: 100vh; }