# Foveal vision reduces neural resources in agent-based game learning

## TL;DR

This paper shows that using a fovea in visual systems can reduce neural resources while maintaining performance in a video game.

## Contribution

The first study to optimize an agent's visual system alongside its decision-making and action generation capabilities.

## Key findings

- Agents with a fovea require fewer neurons and synapses to play Pong.
- Foveal vision maintains performance while reducing computational resources.
- The study integrates visual system optimization with decision-making in agents.

## Abstract

Efficient processing of information is crucial for the optimization of neural resources in both biological and artificial visual systems. In this paper, we study the efficiency that may be obtained via the use of a fovea. Using biologically-motivated agents, we study visual information processing, learning, and decision making in a controlled artificial environment, namely the Atari Pong video game. We compare the resources necessary to play Pong between agents with and without a fovea. Our study shows that a fovea can significantly reduce the neural resources, in the form of number of neurons, number of synapses, and number of computations, while at the same time maintaining performance at playing Pong. To our knowledge, this is the first study in which an agent must simultaneously optimize its visual system, along with its decision making and action generation capabilities. That is, the visual system is integral to a complete agent.