Matthieu Geist

AVEX: What Matters for Animal Vocalization Encoding

Solving robust MDPs as a sequence of static RL problems

Bootstrapping Expectiles in Robust Reinforcement Learning

FALCON-S: Fixed-wing Aerodynamics and Learning Control Suite

Rrls: Robust reinforcement learning suite

Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning

ShiQ: Bringing back Bellman to LLMs

Self-Improving Robust Preference Optimization

Understanding Likelihood Over-optimisation in Direct Alignment Algorithms

Solving robust MDPs as a sequence of static RL problems