Utilization of Deep Reinforcement Learning for saccadic-based object visual search
This work addresses visual search tasks, but it appears incremental as it applies existing deep reinforcement learning methods to a specific domain without claiming major breakthroughs.
The paper tackled the problem of learning saccades for visual object search by developing a system that combines reinforcement learning with a neural network to predict action outcomes, and validated it in environments with randomly generated digit matrices.
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.