Exploiting the potential of deep reinforcement learning for classification tasks in high-dimensional and unstructured data

TL;DR

This paper introduces a framework combining deep autoencoders and reinforcement learning algorithms to improve feature selection efficiency and classification accuracy on high-dimensional, unstructured data.

Contribution

It proposes a novel approach integrating Deep Convolutional Autoencoders with RL algorithms for effective feature selection in complex data.

Findings

Enhanced feature selection reduces the number of features needed for high accuracy

The framework achieves high classification precision on large unstructured datasets

Reinforcement learning algorithms improve the efficiency of feature selection

Abstract

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.