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.AI2026
LLM-Evolved Pattern Generators for Optimal Classical Planning
Windy Phung, Dominik Drexler, Arnaud Lequen +1
Learned heuristics have recently become a competitive alternative to traditional domain-independent heuristics for satisficing planning. Existing approaches, however, focus on impr…
cs.AI2024
Learning Interpretable Classifiers for PDDL Planning
Arnaud Lequen
We consider the problem of synthesizing interpretable models that recognize the behaviour of an agent compared to other agents, on a whole set of similar planning tasks expressed i…