$EvoAl^{2048}$
This work addresses the need for interpretable AI policies in safety-critical products to gain user acceptance, though it appears incremental as it applies existing methods to a specific competition.
The authors tackled the problem of generating interpretable and explainable AI policies for safety-critical applications by developing a model-driven optimization approach to solve the game 2048, resulting in a solution for the GECCO'24 Interpretable Control Competition using the open-source software EvoAl.
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.