Publication Details
Overview
 
 
Senne Deproost, Ann Nowe, Denis Steckelmacher
 

Contribution to journal

Abstract 

Despite many successful attempts at explaining Deep Rein- forcement Learning policies using distillation, it remains difficult to bal- ance the performance-interpretability trade-off and select a fitting surro- gatemodel.Inadditiontothis,traditionaldistillationonlyminimizesthe 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 introduce a new model-agnostic method called Critic- Driven Voronoi State Partitioning, which partitions a black box control policy into regions where a simple class of model can be optimized using gradient descent. By exploiting the critic value network of the original policy, we iteratively introduce new subpolicies in regions with insuffi- cient value, standing in for a measure of policy complexity. The parti- tioning, a Voronoi quantizer, uses nearest neighbor lookups to assign a linear function to each point in the state space resulting in a cell-like diagram. We validate our approach on several well known benchmarks and proof that this distillation approaches the original policy using a reasonable sized set of linear functions.

Reference