English

Policy Optimization with Sparse Global Contrastive Explanations

Machine Learning 2022-07-14 v1

Abstract

We develop a Reinforcement Learning (RL) framework for improving an existing behavior policy via sparse, user-interpretable changes. Our goal is to make minimal changes while gaining as much benefit as possible. We define a minimal change as having a sparse, global contrastive explanation between the original and proposed policy. We improve the current policy with the constraint of keeping that global contrastive explanation short. We demonstrate our framework with a discrete MDP and a continuous 2D navigation domain.

Keywords

Cite

@article{arxiv.2207.06269,
  title  = {Policy Optimization with Sparse Global Contrastive Explanations},
  author = {Jiayu Yao and Sonali Parbhoo and Weiwei Pan and Finale Doshi-Velez},
  journal= {arXiv preprint arXiv:2207.06269},
  year   = {2022}
}

Comments

Accepted at IMLH Workshop, ICML 2022

R2 v1 2026-06-25T00:53:05.252Z