- author = "Paul Templier",
- title = "Leveraging Structures in Evolutionary Neural Policy Search",
- school = "ISAE-Supaero, University of Toulouse",
- year = "2024",
- address = "France",
- month = "22 " # apr,
- keywords = "genetic algorithms, genetic programming, Cartesian Genetic Programming, ANN, ENPS",
-
URL = "
https://depozit.isae.fr/theses/2024/2024_Templier_Paul_D.pdf",
-
URL = "
https://d9w.github.io/TEML/",
- size = "197 pages",
- abstract = "While training an artificial agent for complex tasks like driving a car, mastering a video game, or controlling plasma in a nuclear fusion reactor, innovations can lead to intelligent behavior. In such scenarios, a promising approach is to mimick the natural worlds evolutionary process, which has honed the problem-solving capabilities of animal brains. Evolutionary Neural Policy Search (ENPS) draws inspiration from this concept. It creates a diverse population of brains represented by neural networks, allowing the system to evolve by selectively combining and mutating successful individuals. This thesis delves into the core components of ENPS and their intricate interplay. By analyzing the structures of ENPS, the goal is to design novel policy search methods that enhance these components, ultimately leading to the development of more efficient and effective learning algorithms for complex tasks.",
-
notes = "In english
Summary https://dl.acm.org/doi/pdf/10.1145/3733097.3733101 \cite{Templier:2025:sigevolution}
Supervisors: Emmanuel Rachelson and Dennis Wilson",
