Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models

ArXi:2605.14897v1 Announce Type: new Despite many successful attempts at explaining Deep Reinforcement Learning policies using distillation, it remains difficult to balance the performance-interpretability trade-off and select a fitting surrogate model. In addition to this, traditional distillation only minimizes the distance between the behavior of the original and the surrogate policy while other RL-specific components such as action value are disregarded. To solve this, we