Google Research

Recurrent World Models Facilitate Policy Evolution

Neural Information Processing Systems (2018)

Abstract

A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations. The world model's extracted features are fed into compact and simple policies trained by evolution, achieving state of the art results in various environments. We also train our agent entirely inside of an environment generated by its own internal world model, and transfer this policy back into the actual environment. Interactive version of paper at worldmodels.github.io

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work