yosider/merlin

(Personal experiment) Unsupervised Predictive Memory in a Goal-Directed Agent https://arxiv.org/abs/1803.10760

MERLIN

This is a python implementation of "MERLIN" proposed in the paper :

• "Unsupervised Predictive Memory in a Goal-Directed Agent", DeepMind
  https://arxiv.org/abs/1803.10760

using Chainer.

Currently not working well :(

Any PRs are more than welcome!!