Matthieu Geist

New model improves music creation using user feedback.

A new method enhances strategy learning for agents in multi-agent systems.

Introducing ExpectRL to tackle overestimation in Reinforcement Learning through expectiles.

A new benchmark for testing robust reinforcement learning methods in various environments.

Researchers enhance reinforcement learning with a new framework for uncertain environments.

Contrastive Policy Gradient offers a more efficient way to enhance language models.

A look into how IRL enhances language model performance and diversity.