no code implementations • 30 May 2024 • Bianca Marin Moreno, Margaux Brégère, Pierre Gaillard, Nadia Oudjane
Under partial information on the probability transitions (uncertainty and non-stationarity coming only from external noise, independent of agent state-action pairs), we achieve optimal dynamic regret without prior knowledge of MDP changes.
no code implementations • 30 Nov 2023 • Bianca Marin Moreno, Margaux Brégère, Pierre Gaillard, Nadia Oudjane
Many machine learning tasks can be solved by minimizing a convex function of an occupancy measure over the policies that generate them.
no code implementations • 16 Feb 2023 • Bianca Marin Moreno, Margaux Brégère, Pierre Gaillard, Nadia Oudjane
Integrating renewable energy into the power grid while balancing supply and demand is a complex issue, given its intermittent nature.