Google's AI Dreamer learns how to self-improve over time by mastering Minecraft

Google's AI Dreamer learns how to self-improve over time by mastering Minecraft

A trio of AI researchers at Google's Google DeepMind, working with a colleague from the University of Toronto, report that the AI algorithm Dreamer can learn to self-improve by mastering Minecraft in a short amount of time. In their study published in the journal Nature, Danijar Hafner, Jurgis Pasukonis, Timothy Lillicrap and Jimmy Ba programmed the AI app to play Minecraft without being trained and to achieve an expert level in just nine days.

DeepMind’s 145-page paper on AGI safety may not convince skeptics

Google DeepMind on Wednesday published an exhaustive paper on its safety approach to AGI, roughly defined as AI that can accomplish any task a human can. AGI is a bit of a controversial subject in the AI field, with naysayers suggesting that it’s little more than a pipe dream. Others, including major AI labs like Anthropic, warn that it’s around the corner, and could result in catastrophic harms if steps aren’t taken to implement appropriate saf…

AI masters Minecraft: DeepMind program finds diamonds without being taught

The Dreamer system reached the milestone by ‘imagining’ the future impact of possible decisions. The Dreamer system reached the milestone by ‘imagining’ the future impact of possible decisions.

A new AI benchmark is not only designed to help artificial intelligence compete against each other. The benchmark in Minecraft is also intended to make it easier for amateurs to compare models with each other. read more on t3n.de

According to a study in "Minecraft", a DeepMind AI is dismantling diamonds, which is considered difficult. The learning method should also be used for robots.

Artificial intelligence successfully plays Minecraft

An AI by Google DeepMind has successfully mined diamonds in the open world computer game Minecraft without using human training data. This has been considered a challenge for AI as the task requires many different steps which only offer sparse rewards. Especially the long-term planning required to complete the task has been challenging for AI. The underlying general algorithm has also be used for over 150 other tasks including other games and ro…