theovincent
PhD student at IAS - TU Darmstadt, interested in Reinforcement Learning. Graduated from MVA - ENS Paris-Saclay & Ponts ParisTech.
IAS TU DarmstadtDarmstadt
Pinned Repositories
Website
Dash website to display our results at https://www.multidimensionality-of-aging.net/
ppo
Proximal Policy Optimization Algorithm implementation for the Deep Reinforcement Learning course @ MVA
TrainingCenter
Trains machine learning algorithms to predict the age and the risk of dying for participants of NHANES dataset
3DPointCloudClassification
Challenge to classify 3D point clouds of cities into Ground - Building - Poles - Pedestrians - Cars - Vegetation
coach
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
CPDE
Results of the research to reproduce
PBO
Projected Bellman Operator (PBO). An attempt to learn a parametric Bellman Operator.
theovincent
Self presentation
theovincent's Repositories
theovincent/3DPointCloudClassification
Challenge to classify 3D point clouds of cities into Ground - Building - Poles - Pedestrians - Cars - Vegetation
theovincent/theovincent
Self presentation
theovincent/CPDE
Results of the research to reproduce
theovincent/PBO
Projected Bellman Operator (PBO). An attempt to learn a parametric Bellman Operator.
theovincent/birdClassification
Kaggle class competition on bird classification. Dataset used: Caltech-UCSD Birds-200-2011 bird dataset.
theovincent/coach
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
theovincent/DirectFuturePrediction
Code for the paper "Learning to Act by Predicting the Future", Alexey Dosovitskiy and Vladlen Koltun, ICLR 2017
theovincent/dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
theovincent/double_pendulum
Dual purpose Acrobot and Pendubot Platform
theovincent/HeightmapsGeneration
This project was made on GitLab. In reality, there are four contributors : Auriane Riou, Candice Van Den Bergh, Alex Fauduet and Théo Vincent
theovincent/HouseNumberRecognition
theovincent/lidar-bonnetal
Semantic and Instance Segmentation of LiDAR point clouds for autonomous driving
theovincent/MOPSI
theovincent/ReinforcementLearningWithDemonstration
Problem tackled: How to wisely use expert demonstrations in Reinforcement Learning
theovincent/ruptures
ruptures: change point detection in Python
theovincent/s3-cp-action
GitHub Action for S3 cp
theovincent/SAG_vs_SDCA
The idea of this project is to study different machine learning algorithms
theovincent/sbx
SBX: Stable Baselines Jax (SB3 + Jax)
theovincent/TweetSentimentExtraction
Extract support phrases for sentiment labels : Kaggle Competition
theovincent/website_tutorial
Small website to learn the basics of Dash
theovincent/xport
Python reader and writer for SAS XPORT data transport files.