Evolution and the structure of learning agents

TL;DR

This paper argues that the capabilities of learning agents are fundamentally limited by their informational structure, and evolution is essential for developing the necessary structures to learn effectively in complex environments, implying no universal efficient learning algorithm exists.

Contribution

It introduces a theoretical framework linking evolutionary processes to the development of learning structures, highlighting inherent limitations of finite information agents in complex settings.

Findings

Evolutionary change is essential for creating effective learning structures.

Finite information agents are limited by their informational structure.

Universal efficient learning algorithms are unlikely to exist.

Abstract

This paper presents the thesis that all learning agents of finite information size are limited by their informational structure in what goals they can efficiently learn to achieve in a complex environment. Evolutionary change is critical for creating the required structure for all learning agents in any complex environment. The thesis implies that there is no efficient universal learning algorithm. An agent can go past the learning limits imposed by its structure only by slow evolutionary change or blind search which in a very complex environment can only give an agent an inefficient universal learning capability that can work only in evolutionary timescales or improbable luck.