Neuroevolution Results in Emergence of Short-Term Memory for Goal-Directed Behavior

TL;DR

This paper presents an evolutionary neural network model demonstrating how agents develop short-term memory capabilities for goal-directed behavior through neuroevolution, revealing two mechanisms for memory emergence.

Contribution

The study introduces a neuroevolutionary approach showing how short-term memory can emerge in neural networks for adaptive, goal-directed behavior, highlighting two distinct mechanisms.

Findings

Agents acquire short-term memory during evolution.

Two mechanisms for memory emergence: sensory integration and slow neurodynamics.

Memory enables more adaptive behavioral strategies.

Abstract

Animals behave adaptively in the environment with multiply competing goals. Understanding of the mechanisms underlying such goal-directed behavior remains a challenge for neuroscience as well for adaptive system research. To address this problem we developed an evolutionary model of adaptive behavior in the multigoal stochastic environment. Proposed neuroevolutionary algorithm is based on neuron's duplication as a basic mechanism of agent's recurrent neural network development. Results of simulation demonstrate that in the course of evolution agents acquire the ability to store the short-term memory and, therefore, use it in behavioral strategies with alternative actions. We found that evolution discovered two mechanisms for short-term memory. The first mechanism is integration of sensory signals and ongoing internal neural activity, resulting in emergence of cell groups specialized on alternative actions. And the second mechanism is slow neurodynamical processes that makes possible to code the previous behavioral choice.