Utilization of Deep Reinforcement Learning for saccadic-based object visual search

TL;DR

This paper presents a deep reinforcement learning approach for saccadic eye movements to improve visual object search, validated across various simulated environments with promising results.

Contribution

It introduces a novel system combining reinforcement learning and neural networks to predict saccadic movements for visual search tasks.

Findings

Effective in simulated digit matrix environments

Demonstrates potential for systems mimicking fovea movement

Provides insights for future research directions

Abstract

The paper focuses on the problem of learning saccades enabling visual object search. The developed system combines reinforcement learning with a neural network for learning to predict the possible outcomes of its actions. We validated the solution in three types of environment consisting of (pseudo)-randomly generated matrices of digits. The experimental verification is followed by the discussion regarding elements required by systems mimicking the fovea movement and possible further research directions.