Skip to content
View theovincent's full-sized avatar
🙂
🙂
31 followers · 36 following

Achievements

Achievement: YOLOAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Achievements

Achievement: YOLOAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Organizations

@HMS-AgeVSSurvival @Deep-Learning-and-Aging

Block or report theovincent

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
theovincent/README.md

Hi and welcome! 👋

I'm a PhD student at IAS TU Darmstadt since December 2022 focusing on Reinforcement Learning. This is a brief recap of my past:

  • TU Darmstadt, IAS Master thesis on Reinforcement Learning for value-based methods. (duration: 6 months)
  • ENS Paris-Saclay, MVA - Second year of master focusing on AI. (duration: 1 year)
  • Harvard Medical School - Research on Machine Learning applied to biostatistics. (duration: 8 months)
  • Signality - Research on Deep Learning and Computer Vision applied to football. (duration: 5 months)
  • EDF Lab Chatou - Research on Deep Learning and Computer Vision applied to swimming. (duration: 4 months)
  • Ecole des Ponts ParisTech - Department of Mathematics and Informatics. (duration: 2 years)
  • Lycée du Parc: Preparatory school - MPSI / MP*. (duration: 2 years)

You can find my CV here.

Connect with me:



Pinned Loading

  1. EauDeDQN EauDeDQN Public

    🌸Eau De Q-Network [RLC 25] is a pruning algorithm specifically designed for RL which discovers the final sparsity level of the networks🌸

    Python 4

  2. AdaDQN AdaDQN Public

    ⚡️Adaptive Q-Network [ICLR 25] is one of the first approach to automatically tune RL agents hyperparameters by considering the specificities of reinforcement learning, i.e., non-stationarities⚡️

    Python 6

  3. i-DQN i-DQN Public

    ✨iterated Q-Network [TMLR 25] learns several Bellman iterations in parallel instead of learning them sequentially✨

    Python 7

  4. PBO PBO Public

    🔭Projected Bellman Operator [AAAI 24] learns a parametric Bellman Operator instead of a Q-function🔭 This enable performance improvements at test time!

    Python 1

  5. 3DPointCloudClassification 3DPointCloudClassification Public

    Challenge to classify 3D point clouds of cities into Ground - Building - Poles - Pedestrians - Cars - Vegetation

    Jupyter Notebook 9 1

  6. Deep-Learning-and-Aging/Website Deep-Learning-and-Aging/Website Public

    Dash website to display our results at https://www.multidimensionality-of-aging.net/

    Python 5