• PRObalistic Verification and Counterfactual Explanations for Iterative Decision-Making Tasks
  2026 – 2029 / Austrian Science Fund (FWF)
  Publications: 231227 / 231229

• Probabilistic Verification of Recurrent Neural Networks for Single and Multi-Agent Reinforcement Learning / Marzari, L., & Marchesini, E. (2026). Probabilistic Verification of Recurrent Neural Networks for Single and Multi-Agent Reinforcement Learning. In D. Calvanese (Ed.), Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (pp. 262–270). https://doi.org/10.24963/ijcai.2026/30
  Projects: PROVE-IT (2026–2029) / RobustifAI (2025–2028) / TAIGER (2023–2028)
• A Survey on the Verification of Reinforcement Learning Policies / Marzari, L., Bartocci, E., & Marchesini, E. (2026). A Survey on the Verification of Reinforcement Learning Policies. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (pp. 7958–7966). International Joint Conferences on Artificial Intelligence. https://doi.org/10.24963/ijcai.2026/883
  Projects: PROVE-IT (2026–2029) / RobustifAI (2025–2028) / TAIGER (2023–2028)
• Ɛ-retraining reinforcement learning algorithms / Marzari, L., Liu, C., Donti, P., & Marchesini, E. (2026). Ɛ-retraining reinforcement learning algorithms. Autonomous Agents and Multi-Agent Systems, 40(1), 1–32. https://doi.org/10.1007/s10458-026-09748-6

• PROVE-IT
  2026 / Austria / Website / Project

Soon, this page will include additional information such as reference projects, activities as journal reviewer and editor, memberships in councils and committees, and other research activities.

Until then, please visit Luca Marzari’s research profile in TISS .