Odalric-Ambrym Maillard

Research proposals

Below is a list of research proposal highlights. They are provided to efficiently share detailed, accessible content for potential collaborators or future PhD students and help respond to specific calls or inquiries. Each web page typically provides in-depth motivation, illustrative examples, simplified formalization, and relevant bibliography, to better understand the topic and idea.

Foundations of RL: The Most-confusing Instance Paradigm
Group-sequential Contextual and Geospatial Reinforcement Learning
Reinforcement learning for Spontaneous and Self-Exciting Disturbances
Agroecosystem Gymnasium Simulator Suite
Group-sequential Contextual learning under Changing Therapeutic Landscape
Hierarchical Multi-armed Bandits
Sim-to-real Continual Reinforcement Learning
Optimal Strategies for RLHF Bandits