Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science

TL;DR

This paper analyzes why current AI systems struggle with autonomous learning and proposes a cognitive-inspired architecture that combines observational and active learning with meta-control for improved adaptability.

Contribution

It introduces a novel learning architecture inspired by cognitive science that integrates multiple learning modes and meta-control mechanisms for autonomous AI learning.

Findings

Proposes a hybrid learning framework combining observation and active behavior.

Suggests meta-control signals enable flexible switching between learning modes.

Draws inspiration from biological adaptation to dynamic environments.

Abstract

We critically examine the limitations of current AI models in achieving autonomous learning and propose a learning architecture inspired by human and animal cognition. The proposed framework integrates learning from observation (System A) and learning from active behavior (System B) while flexibly switching between these learning modes as a function of internally generated meta-control signals (System M). We discuss how this could be built by taking inspiration on how organisms adapt to real-world, dynamic environments across evolutionary and developmental timescales.