Projective simulation for classical learning agents: a comprehensive investigation

TL;DR

This paper provides a comprehensive analysis of projective simulation (PS), a novel AI model based on episodic memory, evaluating its efficiency, scalability, and performance across various learning scenarios, and comparing it with established methods.

Contribution

The paper offers the first detailed analysis of PS, demonstrating its scalability, flexibility, and competitive performance relative to Q-learning and classifier systems.

Findings

PS achieves competitive learning efficiency.

Performance scales favorably with problem dimension.

PS demonstrates flexibility across diverse learning scenarios.

Abstract

We study the model of projective simulation (PS), a novel approach to artificial intelligence based on stochastic processing of episodic memory which was recently introduced [H.J. Briegel and G. De las Cuevas. Sci. Rep. 2, 400, (2012)]. Here we provide a detailed analysis of the model and examine its performance, including its achievable efficiency, its learning times and the way both properties scale with the problems' dimension. In addition, we situate the PS agent in different learning scenarios, and study its learning abilities. A variety of new scenarios are being considered, thereby demonstrating the model's flexibility. Furthermore, to put the PS scheme in context, we compare its performance with those of Q-learning and learning classifier systems, two popular models in the field of reinforcement learning. It is shown that PS is a competitive artificial intelligence model of unique properties and strengths.