94% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Neurosci.
Sec. Neuromorphic Engineering
Volume 19 - 2025 | doi: 10.3389/fnins.2025.1547264
Foveal Vision Reduces Neural Resources in Agent-Based Game Learning
Provisionally accepted- 1 Academy for Advanced Interdisciplinary Studies, Peking University, Center for Quantitative Biology, Beijing, China
- 2 Los Alamos National Laboratory, Los Alamos, New Mexico, United States
- 3 National Laboratory of Protein Engineering and Plant Genetic Engineering, School of Life Sciences, Peking University, Center for Bioinformatics, Beijing, China
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.
Keywords: neuromorphic computing, Visual Neuroscience, multi-resolution sensory integration, neural resources, reinforcement learning
Received: 18 Dec 2024; Accepted: 24 Feb 2025.
Copyright: © 2025 Chen, Kunde, Tao and Sornborger. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Runping Chen, Academy for Advanced Interdisciplinary Studies, Peking University, Center for Quantitative Biology, Beijing, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.