- author = "Quentin Vacher and Nicolas Beuve and Mickael Dardaillon and Karol Desnos",
- title = "The {Gegelati} Framework for Efficient and Reproducible Solutions with Tangled Program Graphs",
- old_title = "Advancing Machine Learning with Tangled Program Graphs: The {Gegelati} Framework for Efficient and Reproducible Solutions",
- 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 = "429--449",
- address = "Michigan State University, USA",
- month = jun # " 5-7",
- publisher = "Springer",
- keywords = "genetic algorithms, genetic programming, TPG",
- isbn13 = "978-981-95-6397-5",
-
DOI = "
10.1007/978-981-95-6398-2_21",
-
code_url = "
https://github.com/gegelati/gegelati",
- abstract = "In the last decades, the need to solve complex tasks using machine learning techniques has grown significantly. While deep learning algorithms often achieve state-of-the-art performance, they come with high computational cost. Other methods, such as genetic programming, are able to achieve reasonable results with much lower complexity. Among the genetic programming approaches, the TPG algorithm stands out, particularly in reinforcement learning applications. In this work, we review the Gegelati framework, a framework for learning complex tasks using TPG. This framework allows efficient training with deterministic parallelism and portability. It also supports fast inference through automatic C code generation. Gegelati demonstrates strong performance in classical reinforcement learning tasks involving single discrete actions and is even able to handle applications with multiple continuous actions. Additionally, Gegelati shows promise in classification tasks, achieving some results comparable to deep learning methods.",
-
notes = "lightning talk.
published in 2026 after the workshop",
