- author = "Giorgia Nadizar",
- title = "Interpretable Control with Graph-based Genetic Programming",
- booktitle = "Genetic Programming Theory and Practice XXII",
- year = "2025",
- editor = "Bogdan Burlacu and Fabricio {Olivetti de Franca} and Alexander Lalejini and Stephen Kelly and Wolfgang Banzhaf",
- series = "Genetic and Evolutionary Computation",
- pages = "255--282",
- address = "Michigan State University, USA",
- month = jun # " 5-7",
- publisher = "Springer",
- keywords = "genetic algorithms, genetic programming, Cartesian Genetic Programming, linear genetic programming, ANN, XAI",
- isbn13 = "978-981-95-6397-5",
-
DOI = "
10.1007/978-981-95-6398-2_13",
- abstract = "Cartesian Genetic Programming (CGP) and Linear Genetic Programming (LGP) to a diverse set of benchmark tasks spanning discrete and continuous control. Compared to standard state-of-the-art ANN-based Reinforcement Learning (RL) methods, our approach produces policies with generally competitive performance and significantly smaller, human-readable representations. To assess interpretability, we conduct a systematic analysis of evolved policy graphs, identifying the rationales driving decision-making. While the evolved policies are indeed compact, we find that meaningful interpretation often requires symbolic post-processing, simplification, and visualization, to be truly accessible. Additionally, we highlight the computational inefficiency of current GGP methods relative to RL, suggesting a need for future improvements in optimization and scalability. In summary, our findings on a comprehensive empirical assessment underscore the promise and limitations of GGP for evolving transparent control policies.",
-
notes = "lightning talk.
published in 2026 after the workshop",
