World Models is a framework described by
David Ha and Jürgen Schmidhuber: https://arxiv.org/abs/1803.10122. The framework aims to train an AI agent that can perform well in virtual gaming environments. World Models consists of three main components: Vision (V), Model (M), and Controller (C).
As part of my MSc Artificial Intelligence dissertation at the University of Edinburgh, I implemented World Models from the ground up in Chainer. My implementation was picked up by Chainer and tweeted:
[tweet https://twitter.com/ChainerOfficial/status/1014678023600132096]
David Ha himself also tweeted it:
[tweet https://twitter.com/hardmaru/status/1014681788680060930]
The full implementation and more details can be found at: https://github.com/AdeelMufti/WorldModels.