5 papers
Test-then-Punish: A Statistical Approach to Repeated Games
Aymeric Capitaine, Antoine Scheid, Etienne Boursier +2
We study discounted infinitely repeated games in which players agree on a cooperative mixed action profile but, at each step, observe only the realized pure actions. This form of i…
Online Decision-Focused Learning
Aymeric Capitaine, Maxime Haddouche, Eric Moulines +3
Decision-focused learning (DFL) is an increasingly popular paradigm for training predictive models whose outputs are used in decision-making tasks. Instead of merely optimizing for…
Online Decision-Making in Tree-Like Multi-Agent Games with Transfers
Antoine Scheid, Etienne Boursier, Alain Durmus +2
The widespread deployment of Machine Learning systems everywhere raises challenges, such as dealing with interactions or competition between multiple learners. In that goal, we stu…
Prediction-Aware Learning in Multi-Agent Systems
Aymeric Capitaine, Etienne Boursier, Eric Moulines +2
The framework of uncoupled online learning in multiplayer games has made significant progress in recent years. In particular, the development of time-varying games has considerably…
Optimal Design for Reward Modeling in RLHF
Antoine Scheid, Etienne Boursier, Alain Durmus +4
Reinforcement Learning from Human Feedback (RLHF) has become a popular approach to align language models (LMs) with human preferences. This method involves collecting a large datas…