A Survey on the Verification of Reinforcement Learning Policies

A new survey on arXiv (2607.16210v1) provides a unifying perspective on verification methods for reinforcement learning policies, introducing a taxonomy along three axes: verification paradigm, temporal scope, and guarantees strength. The work aims to clarify relationships among fragmented approaches and identify emerging directions for safety-critical RL deployment.

arXiv:2607.16210v1 Announce Type: new 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.