Why less is sometimes more
- 1 August 2024
- journal article
- research article
- Published by Walter de Gruyter GmbH in it - Information Technology
- Vol. 66 (4-5) , 174-186
Abstract
Explaining and understanding AI-generated policies of control problems is crucial for the acceptance of such policies. Based on an optimisation challenge that took place at GECCO 2024, we describe different solutions for optimising generated policies for the well-known game 2048. At the same time, these generated policies aim to be simpler to understand and, thus, their decisions explainable in contrast to current solutions for 2048, as, e.g., neural network-based models. Our approach uses only Boolean expressions in the policy, and the optimisation shows that such a policy has advantages compared to more complex policy variants. The optimisation generates better results in a shorter time than for non-Boolean expressions. Additionally, the Boolean policies are smaller in size and can be reduced even more when applying existing techniques for term rewriting and simplification. These simplifications, again, may aid in understanding the policy’s decision.Keywords
This publication has 8 references indexed in Scilit:
- Current Trends, Challenges and Techniques in XAI Field; A Tertiary Study of XAI Research2024
- EVOAL: A Domain-Specific Language-Based Approach to Optimisation2023
- A graph-based framework for model-driven optimization facilitating impact analysis of mutation operator propertiesSoftware and Systems Modeling, 2023
- Self-Explanation in Systems of Systems2022
- How can I choose an explainer?2021
- Towards Self-Explainable Cyber-Physical Systems2019
- Keynotes: Towards Self-Explaining Digital Systems: A Design Methodology for the Next Generation2018
- 2048 Without New Tiles Is Still Hard