Reinforcement Learning with Analogical Similarity to Guide Schema Induction and Attention

TL;DR

This paper introduces a novel computational framework combining analogy and reinforcement learning, where analogy guides relational similarity assessment and RL provides feedback, enhancing schema induction and attention mechanisms.

Contribution

It presents a new integrated theory that merges analogy with reinforcement learning to improve relational reasoning and schema induction in AI systems.

Findings

Simulation results demonstrate improved relational similarity assessment.

The framework enhances schema induction and attention mechanisms.

The approach supports higher-order cognitive functions in AI.

Abstract

Research in analogical reasoning suggests that higher-order cognitive functions such as abstract reasoning, far transfer, and creativity are founded on recognizing structural similarities among relational systems. Here we integrate theories of analogy with the computational framework of reinforcement learning (RL). We propose a psychology theory that is a computational synergy between analogy and RL, in which analogical comparison provides the RL learning algorithm with a measure of relational similarity, and RL provides feedback signals that can drive analogical learning. Simulation results support the power of this approach.