tboulet
MVA student @ENS-Paris-Saclay, MEng student at CentraleSupélec. Focus on AI, NLP and Reinforcement Learning.
Pinned Repositories
AI-Agents-for-Games
An implementation in python of some game agents such as AlphaBeta or MCTS, that can be applied to any n-player non deterministic game object that implements the game interface.
AI-Agents-for-Search-Problems
An implementation in python of some algorithms for search problems such as A*, that can be applied to any problem object that follow the SearchProblem interface.
Algorithms-for-Normal-Form-Games
A research project on various algorithms for solving Normal Form Games
Deep-RL-Framework
RLearn is a framework for Deep Reinforcement Learning made by myself. I implements diverse RL algorithms and try to make them learn on various environnements.
EcoJAX
Research project for studying ecosystems of neural agents. In the context of my internship at FLOWERS.
Face-Expression-Recognition
Formation-Reinforcement-Learning
Reinforcement Learning Formation repository, as part of Automatants formations for the CentraleSupélec campus.
gridworld_rl
Implementation of a gridworld environnement with basic RL algorithms on it
Mario-RL
RL on Mario
research-project-template
A template repository, for the objective of combining research and good code practice. It focuses on code structure, modularity, configuration system (Hydra) and logging (tensorboard and WandB)
tboulet's Repositories
tboulet/Formation-Reinforcement-Learning
Reinforcement Learning Formation repository, as part of Automatants formations for the CentraleSupélec campus.
tboulet/AI-Agents-for-Search-Problems
An implementation in python of some algorithms for search problems such as A*, that can be applied to any problem object that follow the SearchProblem interface.
tboulet/gridworld_rl
Implementation of a gridworld environnement with basic RL algorithms on it
tboulet/Colab-Utils
Usefull tools for dealing with colab notebooks
tboulet/Python-Tips-And-Tools
Repo for learning and referencing usefull python tips and tricks or use of libraries.
tboulet/StableBaselines3FullPipeline
Repo for doing RL with SB3 in the most complete and environment-agnostic way, making it easy to deploy.
tboulet/Hackaton42
Machine Learning competition on single-submit classification tasks with highly different train and validation distributions.
tboulet/research-project-template
A template repository, for the objective of combining research and good code practice. It focuses on code structure, modularity, configuration system (Hydra) and logging (tensorboard and WandB)
tboulet/RL-Playground
A web app Reinforcement Learning playground to play with different methods and hyperparameters on different tabular RL environments
tboulet/spinningup
An educational resource to help anyone learn deep reinforcement learning.
tboulet/Deep-RL-Framework
RLearn is a framework for Deep Reinforcement Learning made by myself. I implements diverse RL algorithms and try to make them learn on various environnements.
tboulet/Local-Python-Performance
This project aims to create an easy-to-use package for measuring the performance of python in any machine, in terms of CPU, multiprocessing and GPU (pytorch and tensorflow).
tboulet/Sold-out-Tickets-Detector
A bot for detecting when concerts and festival tickets are sold out
tboulet/tboulet
tboulet/EcoJAX
Research project for studying ecosystems of neural agents. In the context of my internship at FLOWERS.
tboulet/MARL-Benchmark-with-OpenSpiel
A research project for MARL and Game Theory algorithms, using the DeepMind framework OpenSpiel.
tboulet/Algorithms-for-Normal-Form-Games
A research project on various algorithms for solving Normal Form Games
tboulet/IntegOR
IntegOR is a framework based on scipy.optimize that aims to traduce an Operation Research that can be linearized to a linear problem, to solve it.
tboulet/backtracking_algorithm
A framework for backtracking algorithm, as an interface and a solving function
tboulet/Improved-Semantic-Segmentation-for-Night-Drive
Project for improve semantic segmentation on driving images by night, using GAN and lightning methods.
tboulet/package_template
Template for developping a package.
tboulet/QRT-Data-Challenge-Football
Repository for the Data Challenge organized by QRT on match results prediction
tboulet/RL-with-GNN-for-Blackbox-Graph-Optimization
Presentation of my work conducted at InstaDeep during my R&D internship.
tboulet/Spiking-Neural-Networks-Benchmark
A benchmark on various ML tasks for evaluating SNN in comparison to classical ANN neural networks.
tboulet/Airbnb-Price-Prediction
Predicting prices of Airbnb rentals for an ML course at CentraleSupélec
tboulet/Flappy-Bird-with-RL
A school project for solving Flappy Bird with RL agents !
tboulet/Operational-Research
OR methods for Linear Programming and Integer Programming, with a focus on the VM Placement problem
tboulet/PCA-guided-K-means
A benchmark on various K-means initialization method, in particular PCA-guided search, as explained in the paper "PCA-guided search for K-means" by Qin Xu et al.
tboulet/RL-for-Operational-Research
A framework for solving Operational Research problems with tabular RL algorithms.
tboulet/ML-Competition
Kaggle Competition as part of a ML elective course