{"type":"ScholarlyArticle","title":"A Survey on the Verification of Reinforcement Learning Policies","authors":[{"name":"Luca Marzari","slug":"luca-marzari","given":"Luca","family":"Marzari","affiliation":""},{"name":"Ezio Bartocci","slug":"ezio-bartocci","given":"Ezio","family":"Bartocci","affiliation":""},{"name":"Enrico Marchesini","slug":"enrico-marchesini","given":"Enrico","family":"Marchesini","affiliation":""}],"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.","doi":"10.24963/ijcai.2026/883","url":"https://ijcai.org/proceedings/2026/883","pdf":"https://ijcai.org/proceedings/2026/0883.pdf","markdown":"https://ijcai.org/proceedings/2026/883.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/883","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Survey Track","track":"Survey Track","number":883,"pages":{"first":7958,"last":7966},"keywords":["Agent-based and Multi-agent Systems: Formal verification, validation and synthesis","Machine Learning: Reinforcement learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}