Projective simulation applied to the grid-world and the mountain-car problem

TL;DR

This paper evaluates the projective simulation (PS) model in complex AI tasks like grid-world and mountain-car, demonstrating its competitive performance compared to existing reinforcement learning models in large, continuous input spaces.

Contribution

It extends the application of the PS model to more challenging environments, showing its effectiveness beyond simple tasks.

Findings

PS performs well in grid-world and mountain-car tasks

PS is competitive with standard reinforcement learning models

Demonstrates applicability of PS to complex, continuous environments

Abstract

We study the model of projective simulation (PS) which is a novel approach to artificial intelligence (AI). Recently it was shown that the PS agent performs well in a number of simple task environments, also when compared to standard models of reinforcement learning (RL). In this paper we study the performance of the PS agent further in more complicated scenarios. To that end we chose two well-studied benchmarking problems, namely the "grid-world" and the "mountain-car" problem, which challenge the model with large and continuous input space. We compare the performance of the PS agent model with those of existing models and show that the PS agent exhibits competitive performance also in such scenarios.