An Evolutionary Algorithm for Error-Driven Learning via Reinforcement

TL;DR

This paper introduces a theoretical framework demonstrating how complex behaviors can be learned through reinforcement alone, without explicit error-driven mechanisms, by evolving neural network topologies.

Contribution

It proposes a novel evolutionary algorithm that enables neural networks to learn complex tasks solely based on performance reinforcement signals.

Findings

Networks can evolve to solve large-scale problems using only reinforcement feedback.

The framework offers insights into biological learning processes.

Potential applications in designing adaptive artificial intelligence systems.

Abstract

Although different learning systems are coordinated to afford complex behavior, little is known about how this occurs. This article describes a theoretical framework that specifies how complex behaviors that might be thought to require error-driven learning might instead be acquired through simple reinforcement. This framework includes specific assumptions about the mechanisms that contribute to the evolution of (artificial) neural networks to generate topologies that allow the networks to learn large-scale complex problems using only information about the quality of their performance. The practical and theoretical implications of the framework are discussed, as are possible biological analogs of the approach.