The Robot Brains Podcast cover image

Ilya Sutskever explains the origins of deep learning

The Robot Brains Podcast

00:00

How to Train a Robot to Solve a Rubic Scheme

Reinforcement learning can be extremely successful if you have the ability to generate a very large amount of experience against some kind of a simulator. The training was done entirely in simulation, so that its extra heart and its requires the neural net to be very adaptive. Another important result in openinas history, was to use the same exact approach to train a robot to solve the rubic scheme.

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