no code implementations • 7 May 2024 • Paul Templier, Emmanuel Rachelson, Antoine Cully, Dennis G. Wilson
Here, we highlight the phenomenon of genetic drift where the actor genome and the ES population distribution progressively drift apart, leading to injection having a negative impact on the ES.
no code implementations • 7 May 2024 • Paul Templier, Luca Grillotti, Emmanuel Rachelson, Dennis G. Wilson, Antoine Cully
Evolution Strategies (ES) are effective gradient-free optimization methods that can be competitive with gradient-based approaches for policy search.
1 code implementation • 28 Feb 2023 • Kévin Cortacero, Brienne McKenzie, Sabina Müller, Roxana Khazen, Fanny Lafouresse, Gaëlle Corsaut, Nathalie Van Acker, François-Xavier Frenois, Laurence Lamant, Nicolas Meyer, Béatrice Vergier, Dennis G. Wilson, Hervé Luga, Oskar Staufer, Michael L. Dustin, Salvatore Valitutti, Sylvain Cussat-Blanc
An unresolved issue in contemporary biomedicine is the overwhelming number and diversity of complex images that require annotation, analysis and interpretation.
no code implementations • 7 Dec 2022 • Paul-Antoine Le Tolguenec, Emmanuel Rachelson, Yann Besse, Dennis G. Wilson
In this work, we use a recently proposed definition of intrinsic motivation, Curiosity, in an evolutionary policy search method.
no code implementations • 11 Oct 2022 • Kaitlin Maile, Dennis G. Wilson, Patrick Forré
Incorporating equivariance to symmetry groups as a constraint during neural network training can improve performance and generalization for tasks exhibiting those symmetries, but such symmetries are often not perfectly nor explicitly present.
no code implementations • 5 Oct 2022 • Valentin Guillet, Dennis G. Wilson, Carlos Aguilar-Melchor, Emmanuel Rachelson
Although transfer learning is considered to be a milestone in deep reinforcement learning, the mechanisms behind it are still poorly understood.
no code implementations • 5 Oct 2022 • Valentin Guillet, Dennis G. Wilson, Carlos Aguilar-Melchor, Emmanuel Rachelson
Learning a good state representation is a critical skill when dealing with multiple tasks in Reinforcement Learning as it allows for transfer and better generalization between tasks.
1 code implementation • 17 Feb 2022 • Kaitlin Maile, Emmanuel Rachelson, Hervé Luga, Dennis G. Wilson
Neurogenesis in ANNs is an understudied and difficult problem, even compared to other forms of structural learning like pruning.
no code implementations • 22 Jun 2021 • Kaitlin Maile, Erwan Lecarpentier, Hervé Luga, Dennis G. Wilson
Differentiable Architecture Search (DARTS) is a recent neural architecture search (NAS) method based on a differentiable relaxation.
Ranked #10 on Neural Architecture Search on CIFAR-100