ClementRomac
Research Scientist at π€ @huggingface, PhD. student at Inria @flowersteam . Studying how autonomous Deep RL agents π€ can leverage large Language Models π
Hugging Face, InriaBordeaux, France
Pinned Repositories
clementromac.github.io
DeepQLearning-TicTacToe
Deep QLearning to solve TicTacToe
gym-tictactoe
Gym TicTacToe is a light Tic-Tac-Toe environment for OpenAI Gym.
Teaching
Teaching materials
Grounding_LLMs_with_online_RL
We perform functional grounding of LLMs' knowledge in BabyAI-Text
Interactive_DeepRL_Demo
In-browser interactive demo of Deep Reinforcement Learning agents' adaptation to unknown 2D tasks.
lamorel
Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).
TeachMyAgent
TeachMyAgent is a testbed platform for Automatic Curriculum Learning methods in Deep RL.
simulate
π’ Creating and sharing simulation environments for embodied and synthetic data research
Minecraft-Reinforcement-Learning
Deep Recurrent Q-Learning vs Deep Q Learning on a simple Partially Observable Markov Decision Process with Minecraft
ClementRomac's Repositories
ClementRomac/gym-tictactoe
Gym TicTacToe is a light Tic-Tac-Toe environment for OpenAI Gym.
ClementRomac/Teaching
Teaching materials
ClementRomac/DeepQLearning-TicTacToe
Deep QLearning to solve TicTacToe
ClementRomac/clementromac.github.io
ClementRomac/DeepLearningBookPlayground
This repository aims to put what I've learned from the DeepLearning Book in practice.
ClementRomac/FitBit_Project
Mobile web application for IoT and Mobile Web Development classes at Ingesup.
ClementRomac/MathadorProject
C# Mathador game for the .Net class at Ingesup
ClementRomac/GrooveYou
GrooveYou is a website where users can share music with friends.
ClementRomac/High-School-Pape-Clement-app
Android application for the high school Pape ClΓ©ment for the Android Develoment class at Ingesup.
ClementRomac/NodeJS_CLI_Project
NodeJS CLI to access marvel heros for the NodeJS class at Ingesup.