Brain Networks Laboratory (Choe Lab)

[Schmidhuber] World models

Apr 3, 2018

https://worldmodels.github.io

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

PDF

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 ]