A neural net architecture based on principles of neural plasticity and development evolves to effectively catch prey in a simulated environment

TL;DR

This paper introduces a neural network architecture inspired by biological neural plasticity and development, enabling artificial agents to adaptively and dynamically respond to sensory inputs for prey capture in a simulated environment.

Contribution

The proposed architecture mimics biological brain development and plasticity, allowing real-time, dynamic responses without precomputed optimal behaviors, optimized via evolutionary algorithms.

Findings

Effective prey capture in simulation

Rapid response to sensory changes

Potential application in autonomous robots

Abstract

A profound challenge for A-Life is to construct agents whose behavior is 'life-like' in a deep way. We propose an architecture and approach to constructing networks driving artificial agents, using processes analogous to the processes that construct and sculpt the brains of animals. Furthermore the instantiation of action is dynamic: the whole network responds in real-time to sensory inputs to activate effectors, rather than computing a representation of the optimal behavior and sending off an encoded representation to effector controllers. There are many parameters and we use an evolutionary algorithm to select them, in the context of a specific prey-capture task. We think this architecture may be useful for controlling small autonomous robots or drones, because it allows for a rapid response to changes in sensor inputs.