Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression

arXiv:2403.14328v1 Announce Type: cross
Abstract: Recent advancements in reinforcement learning (RL) have led to remarkable achievements in robot locomotion capabilities. However, the complexity and ``black-box'' nature of neural network-based RL policies hinder their interpretability and broader acceptance, particularly in applications demanding high levels of safety and reliability. This paper introduces a novel approach to distill neural RL policies into more interpretable forms using Gradient Boosting Machines (GBMs), Explainable Boosting Machines (EBMs) and Symbolic Regression. By leveraging the inherent interpretability of …

abstract applications arxiv boosting box capabilities complexity cs.ai cs.lg cs.ro gradient hinder however interpretability machines nature network neural network regression reinforcement reinforcement learning robot safety type