Evolution of Inherently Interpretable Visual Control Policies

Created by W.Langdon from gp-bibliography.bib Revision:1.8464

@InProceedings{de-la-torre:2025:GECCO,

• author = "Camilo {De La Torre} and Giorgia Nadizar and Yuri Lavinas and Herve Luga and Dennis Wilson and Sylvain Cussat-Blanc",
• title = "Evolution of Inherently Interpretable Visual Control Policies",
• booktitle = "Proceedings of the 2025 Genetic and Evolutionary Computation Conference",
• year = "2025",
• editor = "Ryan Urbanowicz and Will N. Browne",
• pages = "358--367",
• address = "Malaga, Spain",
• series = "GECCO '25",
• month = "14-18 " # jul,
• organisation = "SIGEVO",
• publisher = "Association for Computing Machinery",
• publisher_address = "New York, NY, USA",
• keywords = "genetic algorithms, genetic programming, Evolutionary Machine Learning",
• isbn13 = "979-8-4007-1465-8",
• URL = "https://doi.org/10.1145/3712256.3726332",
• DOI = "doi:10.1145/3712256.3726332",
• size = "10 pages",
• abstract = "Vision-based decision-making tasks encompass a wide range of applications, including safety-critical domains where trustworthiness is as key as performance. These tasks are often addressed using Deep Reinforcement Learning (DRL) techniques, based on Artificial Neural Networks (ANNs), to automate sequential decision making. However, the {"}black-box{"} nature of ANNs limits their applicability in these settings, where transparency and accountability are essential. To address this, various explanation methods have been proposed; however, they often fall short in fully elucidating the decision-making pipeline of ANNs, a critical aspect for ensuring reliability in safety-critical applications. To bridge this gap, we propose an approach based on Graph-based Genetic Programming (GGP) to generate transparent policies for vision-based control tasks. Our evolved policies are constrained in size and composed of simple and well-understood operational modules, enabling inherent interpretability. We evaluate our method on three Atari games, comparing explanations derived from common explainability techniques to those derived from interpreting the agent's true computational graph. We demonstrate that interpretable policies offer a more complete view of the decision process than explainability methods, enabling a full comprehension of competitive game-playing policies.",
• notes = "GECCO-2025 EML A Recombination of the 34th International Conference on Genetic Algorithms (ICGA) and the 30th Annual Genetic Programming Conference (GP)",

}

Genetic Programming entries for Camilo De La Torre Giorgia Nadizar Yuri Lavinas Herve Luga Dennis G Wilson Sylvain Cussat-Blanc

Citations