$EvoAl^{2048}$

TL;DR

A model-driven-based optimisation is applied to search for an interpretable and explainable policy that solves the game 2048 and aims to develop an approach for creating interpretable policies that are easy to adapt to new ideas.

Abstract

As AI solutions enter safety-critical products, the explainability and interpretability of solutions generated by AI products become increasingly important. In the long term, such explanations are the key to gaining users' acceptance of AI-based systems' decisions. We report on applying a model-driven-based optimisation to search for an interpretable and explainable policy that solves the game 2048. This paper describes a solution to the GECCO'24 Interpretable Control Competition using the open-source software EvoAl. We aimed to develop an approach for creating interpretable policies that are easy to adapt to new ideas.

Figures (3)

• Figure 1: Depiction of our generation process
• Figure 2: Excerpt of our policy model
• Figure 3: Overview of the fitness values over time