[Schmidhuber] World models
Apr 3, 2018
An ambitious project by David Ha and Juergen Schmidhuber..
World Models
Can agents learn inside of their own dreams?
DAVID HA
Google Brain
Tokyo, Japan
JÜRGEN SCHMIDHUBER
NNAISENSE
Swiss AI Lab, IDSIA (USI & SUPSI)
2018
NIPS 2018
Paper
YouTube
Talk
Download
Abstract
We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the environment. By using features extracted from the world model as inputs to an agent, we can train a very compact and simple policy that can solve the required task. We can even train our agent entirely inside of its own dream environment generated by its world model, and transfer this policy back into the actual environment.
← Back to all articles Quick Navigation: Next:[ j ] – Prev:[ k ] – List:[ l ]