$EvoAl^{2048}$

TL;DR

This paper presents EvoAl, an open-source tool that uses model-driven optimization to develop interpretable AI policies for playing the game 2048, emphasizing explainability for safety-critical applications.

Contribution

It introduces a novel approach using model-driven optimization with EvoAl to generate interpretable policies for 2048, addressing explainability in AI decision-making.

Findings

Successfully developed an interpretable 2048 policy

Won the GECCO'24 Interpretable Control Competition

Demonstrated adaptability of the approach

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.