Claire Vernade

Non-Stationary Lipschitz Bandits

Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning

Quantization-Free Autoregressive Action Transformer

Partially Observable Reinforcement Learning with Memory Traces

Is multitask learning all you need in continual learning?

Online Decision Deferral under Budget Constraints

A Pontryagin Perspective on Reinforcement Learning