Recurrent World Models Facilitate Policy Evolution
Machine Learning
2018-09-07 v1 Machine Learning
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 https://worldmodels.github.io
Cite
@article{arxiv.1809.01999,
title = {Recurrent World Models Facilitate Policy Evolution},
author = {David Ha and Jürgen Schmidhuber},
journal= {arXiv preprint arXiv:1809.01999},
year = {2018}
}
Comments
To appear at NIPS 2018, selected for an oral presentation. arXiv admin note: substantial text overlap with arXiv:1803.10122