Lukas is an AI researcher who aims to create autonomous agents that can efficiently learn to solve complex decision-making tasks in the real world.

Ghada is a research scientist developing efficient methods for model adaptation and continuous learning under non-stationary conditions. Her current research interests are continual learning, model merging, sparsity, and reinforcement learning.

Gaspard's research focuses on RL in POMDPs, with an interest in sequence modeling, representation learning, world models, asymmetric learning, and generalization. 

Shihan's research focuses on reinforcement learning algorithms that can learn optimal policies through efficient and effective human-agent or agent-agent interactions, particularly in the context of communication.