DeepMind's new reinforcement learning system

In a new paper published last week, scientists at AI research lab DeepMind claimed to have taken the “first steps to train an agent capable of playing many different games without needing human interaction data.”

Their new AI system, which they describe as “open-ended learning,” includes a 3D environment with realistic dynamics and deep reinforcement learning agents that can learn to solve a wide range of challenges.

The new system, according to DeepMind’s AI researchers, is an “important step toward creating more general agents with the flexibility to adapt rapidly within constantly changing environments.”

The paper's findings show some impressive advances in applying reinforcement learning to complicated problems. But they are also a reminder of how far current systems are from achieving the kind of general intelligence capabilities that the AI community has been coveting for decades.

Read the article on TechTalks.

For more on AI research:

• Can AI learn to reason about the world like children?

• The future of deep learning, according to its pioneers

• Machine learning security needs new perspectives and incentives

• 4 key misunderstandings in AI