Proceedings

A Survey on the Verification of Reinforcement Learning Policies

Luca Marzari, Ezio Bartocci, Enrico Marchesini

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Survey Track. Pages 7958-7966.

https://doi.org/10.24963/ijcai.2026/883

Keywords

  • Agent-based and Multi-agent Systems: Formal verification, validation and synthesis
  • Machine Learning: Reinforcement learning

Abstract

Reinforcement learning (RL) is increasingly applied in complex, safety-critical domains, yet the lack of rigorous behavioral guarantees for neural network-based policies remains a major barrier to deployment. Recent advances in policy expressiveness and scale have intensified this challenge, leading to a rapidly growing but conceptually fragmented body of work on RL policy verification. This survey provides a unifying perspective on RL verification methods. We introduce a taxonomy that clarifies relationships among existing approaches along three axes: verification paradigm (formal versus probabilistic), temporal scope (step-wise versus multi-step), and guarantees strength. Beyond taxonomy, we unify underlying theoretical foundations, make implicit assumptions and limitations explicit, and identify emerging directions.

Luca Marzari, Ezio Bartocci, and Enrico Marchesini. 2026. A Survey on the Verification of Reinforcement Learning Policies. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 7958–7966. https://doi.org/10.24963/ijcai.2026/883
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards