@article{offpolicytemporaldifferencelearningfor,
  title = {Off-Policy Temporal Difference Learning for Perturbed Markov Decision Processes: Theoretical Insights and Extensive Simulations},
  author = {Ali Forootani and Raffaele Iervolino and Massimo Tipaldi and Mohammad Khosravi},
  year = {2025},
  eprint = {2502.18415},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.18415v2},
}