3 papers
cs.LG2026
Pareto Q-Learning with Reward Machines
Arnaud Lequen, Clément Legrand-Lixon, Léo Saulières
We present Pareto Q-Learning with Reward Machines (PQLRM), a multi-objective reinforcement learning algorithm for tasks whose reward structure is specified by a set of reward machi…
cs.AI2025
A Survey of Explainable Reinforcement Learning: Targets, Methods and Needs
Léo Saulières
The success of recent Artificial Intelligence (AI) models has been accompanied by the opacity of their internal mechanisms, due notably to the use of deep neural networks. In order…
cs.AI2024
Backward explanations via redefinition of predicates
Léo Saulières, Martin C. Cooper, Florence Dupin de Saint Cyr
History eXplanation based on Predicates (HXP), studies the behavior of a Reinforcement Learning (RL) agent in a sequence of agent's interactions with the environment (a history), t…