Pinned Repositories
academic-kickstart
aheuillet.github.io
ARNN
Collective-eXplainable-supplementary
Supplementary material for the article Collective eXplainable AI: Explaining Cooperative strategies and agent contribution in Multiagent Reinforcement Learning with Shapley Values
covid19-tomo
D-DARTS
Official implementation of the D-DARTS paper.
database-php-middleware
gold_deep_rl
Training a deep RL agent to play Pokemon Gold/Silver using only vision.
NASiam
Official implementation of the NASiam paper.
Vicon-ROS2
A C++ bridge between ROS2 and Vicon, built using DataStream SDK
aheuillet's Repositories
aheuillet/NASiam
Official implementation of the NASiam paper.
aheuillet/gold_deep_rl
Training a deep RL agent to play Pokemon Gold/Silver using only vision.
aheuillet/Vicon-ROS2
A C++ bridge between ROS2 and Vicon, built using DataStream SDK
aheuillet/D-DARTS
Official implementation of the D-DARTS paper.
aheuillet/ARNN
aheuillet/academic-kickstart
aheuillet/aheuillet.github.io
aheuillet/Collective-eXplainable-supplementary
Supplementary material for the article Collective eXplainable AI: Explaining Cooperative strategies and agent contribution in Multiagent Reinforcement Learning with Shapley Values
aheuillet/covid19-tomo
aheuillet/database-php-middleware
aheuillet/forest-fire
aheuillet/genetic_backpack
Backpack problem solver implemented using genetic algorithms
aheuillet/Makers-Porte
aheuillet/MUNIT
Multimodal Unsupervised Image-to-Image Translation
aheuillet/parrainage
App for the sponsorship evening contest at ENSEIRB-MATMECA
aheuillet/Playback-Reality
A new way of learning, using pre-recorded movements and Microsoft Hololens
aheuillet/poke-env
A python interface for training Reinforcement Learning bots to battle on pokemon showdown
aheuillet/pokemon-showdown
Pokémon battle simulator.
aheuillet/pygame-maze-runner
A maze runner built using PyGame
aheuillet/ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
aheuillet/RoadGAN