This paper presents a framework for efficiently learning feature selection policies which use less features to reach a high classification precision on large unstructured data. It uses a Deep Convolutional Autoencoder (DCAE) for learning compact feature spaces, in combination with recently-proposed Reinforcement Learning (RL) algorithms as Double DQN and Retrace.
@article{arxiv.1912.09595,
title = {Exploiting the potential of deep reinforcement learning for classification tasks in high-dimensional and unstructured data},
author = {Johan S. Obando-Ceron and Victor Romero Cano and Walter Mayor Toro},
journal= {arXiv preprint arXiv:1912.09595},
year = {2019}
}