3 papers
cs.LG2023
One-Step Distributional Reinforcement Learning
Mastane Achab, Reda Alami, Yasser Abdelaziz Dahou Djilali +2
Reinforcement learning (RL) allows an agent interacting sequentially with an environment to maximize its long-term expected return. In the distributional RL (DistrRL) paradigm, the…
cs.AI2023
Regularization of the policy updates for stabilizing Mean Field Games
Talal Algumaei, Ruben Solozabal, Reda Alami +3
This work studies non-cooperative Multi-Agent Reinforcement Learning (MARL) where multiple agents interact in the same environment and whose goal is to maximize the individual retu…
cs.LG2023
Restarted Bayesian Online Change-point Detection for Non-Stationary Markov Decision Processes
Reda Alami, Mohammed Mahfoud, Eric Moulines
We consider the problem of learning in a non-stationary reinforcement learning (RL) environment, where the setting can be fully described by a piecewise stationary discrete-time Ma…