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

2019/12/19 by Johan Obando-Ceron, Obando-Ceron, Johan S., Víctor Romero-Cano +3
Computer Science · #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Neural Networks and Applications #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.1912.09595

openalex publication_date 2019/12/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?
• Learning What Data to Learn
• Classification with Costly Features using Deep Reinforcement Learning
• Supervised Dimensionality Reduction and Image Classification Utilizing Convolutional Autoencoders
• Deep Learning: A Tutorial