arXiv:2608.09967v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) agents achieve strong performance in complex environments, yet their decision-making processes remain difficult to interpret. We introduce SPOT (Sampling Policy Observation Tree), a novel model-agnostic, sampling-based framework for interpreting DRL policies. Given access to the policy and an environment simulator, SPOT constructs an interpretable finite-horizon tree by sampling actions and recursively simulating the resulting successor states. The tree provides an empirical representation of the policy's action
Improves interpretability in RL via lookahead explanations, enabling decision-makers to audit policies, debug failures, and build trust for deployment in high-stakes control.
Published to Cognify News · Week 33, 2026