Active inference is a process theory of the brain that states that all living organisms infer actions in order to minimize their (expected) free energy. However, current experiments are limited to predefined, often discrete, state spaces. In this paper we use recent advances in deep learning to learn the state space and approximate the necessary probability distributions to engage in active inference.
Cite
@article{arxiv.2001.11841,
title = {Learning Perception and Planning with Deep Active Inference},
author = {Ozan Çatal and Tim Verbelen and Johannes Nauta and Cedric De Boom and Bart Dhoedt},
journal= {arXiv preprint arXiv:2001.11841},
year = {2020}
}