@article{paretoqlearningwithrewardmachines,
  title = {Pareto Q-Learning with Reward Machines},
  author = {Arnaud Lequen and Clément Legrand-Lixon and Léo Saulières},
  year = {2026},
  eprint = {2606.19134},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.19134},
}