Publication Details
Overview
 
 
Senne Deproost, Ann Nowe, Mehrdad Asadi
 

Unpublished contribution to conference

Abstract 

Deep Reinforcement Learning (DRL) achieves state-of-the-art for controller generation. However, it relies on a monolith neural policy to perform, reducing transparency and user trust. We distill a DRL policy into a set of human-readable models by partitioning the state space in regions. Using a hierarchy of linear Support Vector Machines (SVM) we show a close approximation of the original policy using simple linear functions

Reference