Centre Inria de l'Université de Rennes

AI & ML interests

informatics

Recent Activity

misovalko  authored a paper about 2 months ago

Optimal Design for Reward Modeling in RLHF

misovalko  authored a paper about 2 months ago

Sharp Deviations Bounds for Dirichlet Weighted Sums with Application to analysis of Bayesian algorithms

misovalko  authored a paper about 2 months ago

KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal

View all activity

Team members 86