Tools

Learning to play Minecraft with Video PreTraining

Source: OpenAI News 23 Jun 2022

Listen to Brief

AI audio in English, based on the NadiAI brief and original source.

Brief

We trained a neural network to play Minecraft by Video PreTraining (VPT) on a massive unlabeled video dataset of human Minecraft play, while using only a small amount of labeled contractor data. With fine-tuning, our model can learn to craft diamond tools, a task that usually takes proficient humans over 20 minutes (24,000 actions). Our model uses the native human interface of keypresses and mouse movements, making it quite general, and represents a step towards general computer-using agents.

Why It Matters

Pendekatan ini menunjukkan arah baru bagi agen yang menggunakan antara muka manusia sambil mengurangkan kebergantungan pada data berlabel.

Keep Reading on NadiAI

Selected Related Articles