Naturally Interpretable Control Policies via Graph-Based Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.7650

@InProceedings{Nadizar:2024:EuroGP,

• author = "Giorgia Nadizar and Eric Medvet and Dennis G. Wilson",
• editor = "Mario Giacobini and Bing Xue and Luca Manzoni",
• title = "Naturally Interpretable Control Policies via Graph-Based Genetic Programming",
• booktitle = "EuroGP 2024: Proceedings of the 27th European Conference on Genetic Programming",
• year = "2024",
• volume = "14631",
• series = "LNCS",
• publisher = "Springer",
• address = "Aberystwyth",
• month = "3-5 " # apr,
• organisation = "EvoStar, Species",
• note = "Best paper",
• keywords = "genetic algorithms, genetic programming, Cartesian Genetic Programming",
• pages = "73--89",
• abstract = "In most high-risk applications, interpretability is crucial for ensuring system safety and trust. However, existing research often relies on hard-to-understand, highly parameterized models, such as neural networks. In this paper, we focus on the problem of policy search in continuous observations and actions spaces. We leverage two graph-based Genetic Programming (GP) techniques, Cartesian Genetic Programming (CGP) and Linear Genetic Programming (LGP), to develop effective yet interpretable control policies. Our experimental evaluation on eight continuous robotic control benchmarks shows competitive results compared to state-of-the-art Reinforcement Learning (RL) algorithms. Moreover, we find that graph-based GP tends towards small, interpretable graphs even when competitive with RL. By examining these graphs, we are able to explain the discovered policies, paving the way for trustworthy AI in the domain of continuous control.",
• isbn13 = "978-3-031-56957-9",
• DOI = "doi:10.1007/978-3-031-56957-9_5",
• notes = "Part of \cite{Giacobini:2024:GP} EuroGP'2024 held in conjunction with EvoCOP2024, EvoMusArt2024 and EvoApplications2024",

}

Genetic Programming entries for Giorgia Nadizar Eric Medvet Dennis G Wilson

Citations