Some recent projects
Built a robot AI with Unity that acts based on player input using a deep language model to understand any text input and find the closest action of its list.
Read the articleBuilt a demo with Unity where you can have a live conversation with NPC. The AI answers using OpenAI gpt3 and is voiced by Replica.
More infoBuilt a demo where two NPC have a conversation generated by GPT-J and voiced by ReplicaAI.
More infoDog AI powered by a deep language model that helps it understand any human order and find the closest action of its list.
More infoAhoy young pirate 🏴☠🦜! Will you be able to beat our pAIrate? This game was made during International Summer School on AI and Games 3rd Edition (05. - 09.07.2021). This AI was trained with Deep Reinforcement Learning, using the Unity ML-Agents toolkit!
Start PlayingBattle Tanks! is a game based on Tanks! by Unity, where you need to destroy your smart AI opponent. The AI is made using Deep Reinforcement Learning and Unity ML-Agents.
Start Playing[NEW VERSION IN PROGRESS] A free course about Deep Reinforcement Learning, where we'll learn the main algorithms, and how to implement them with Tensorflow and PyTorch.
Start LearningThe Mayan Adventure is an open-source reinforcement learning environment for Unity ML-Agents. In this environment, you train your agent (Indie) to find the golden statue in this dangerous environment full of traps.
Check the projectMy recent talks
Curiosity Driven Learning is one of the most exciting and promising strategy in deep reinforcement learning: we create agents that are able to produce rewards and learn from them. In this workshop, you’ll learn what is curiosity, how it works, and understand the process of how an agent generates this intrinsic reward using a trained agent in a video game environment. By the end of this workshop, you'll be able to understand how curiosity driven learning agents work and the main elements needed to implement them.
Learn More