PulseAugur
EN
LIVE 18:23:31

OpenAI trains Minecraft agent using unlabeled video and imitation learning

OpenAI has developed a new method called Video PreTraining (VPT) to train AI agents using vast amounts of unlabeled online video data. This technique involves first training an inverse dynamics model on a small set of labeled videos to predict actions, which then labels a larger dataset. The trained model, demonstrated in Minecraft, can perform complex tasks like crafting diamond tools, showcasing a step towards general AI agents capable of interacting with computer interfaces. AI

RANK_REASON OpenAI released a paper detailing a new training methodology for AI agents using video data, which is a research advancement.

Read on OpenAI News →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

OpenAI trains Minecraft agent using unlabeled video and imitation learning

COVERAGE [1]

  1. OpenAI News TIER_1 English(EN) ·

    Learning to play Minecraft with Video PreTraining

    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 tak…