2 papers
cs.LG2026
PAC-Bayesian Reinforcement Learning Trains Generalizable Policies
Abdelkrim Zitouni, Mehdi Hennequin, Juba Agoun +3
We derive a novel PAC-Bayesian generalization bound for reinforcement learning that explicitly accounts for Markov dependencies in the data, through the chain's mixing time. This c…
cs.LG2025
Multi-View Majority Vote Learning Algorithms: Direct Minimization of PAC-Bayesian Bounds
Mehdi Hennequin, Abdelkrim Zitouni, Khalid Benabdeslem +2
The PAC-Bayesian framework has significantly advanced the understanding of statistical learning, particularly for majority voting methods. Despite its successes, its application to…