R

reinforcement-learning

Projet pédagogique en algorithmie et intelligence artificielle consistant à créer un agent (Kevin) capable de résoudre un labyrinthe.

Le projet explore plusieurs approches :

Génération de labyrinthes (DFS, Prim) Algorithmes de recherche de chemin (A*, Dijkstra) Apprentissage supervisé (Imitation Learning avec CNN) Apprentissage par renforcement (Deep Q-Network)

Des outils de visualisation permettent de générer des images et des GIFs montrant Kevin se déplacer dans le labyrinthe.

Projet réalisé dans le cadre de la formation Développeur en Intelligence Artificielle (Simplon).

A flexible robotics toolkit that supports real-time environments and is AI friendly for IRL hardware.

Code associated with the CDC 2025 paper "Control of a bi-stable genetic system via parallelized reinforcement learning".

Fast Flexible Replay Buffer Library

SIA - C++/Python library for model-based stochastic estimation and optimal control

Suppressing bacteria in microbial communities with reinforcement learning

Test project for neural networks - Handwritten digit recognition on MNIST dataset

An OpenAI Gym for Shopping Cart Reinforcement Learning.

A very simple example of using RL in real life using servo motors.

Learn to drive an radio-controlled car using only a camera. Uses a DonkeyCar simulation, SAC and a VAE. By Winder Research.

Examples demonstrating Kullback-Leibler divergence.

A simple implementation of vanilla greedy-GQ, a reinforcement learning algorithm.

A simplified version of "Cliffworld" in an OpenAI Gym Environment

Simple and efficient data recording for OpenAI Gym reinforcement learning environments. https://doctorj.gitlab.io/gymbag/