The Gradient: Perspectives on AI cover image

Marc Bellemare: Distributional Reinforcement Learning

The Gradient: Perspectives on AI

00:00

Deep Reinforcement Learning in the Real World

Google Brain has been working with Loon to apply deep reinforcement learning in the real world. The project involved controlling balloons that would fly about 20 kilometers high in the air and roam the earth for months or even ideally the gold would have been years on it. Because these systems are pretty under actuated there is a real need to apply reinforcement learning to get the most out of these systems. So just from an RO perspective this was a perfect fit for Deep RL.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app