Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning

TL;DR

This paper introduces a novel framework using Adversarial Inverse Reinforcement Learning to provide global explanations for deep reinforcement learning models, enhancing interpretability by summarizing their decision-making processes.

Contribution

It presents a new approach that leverages inverse reinforcement learning to interpret and explain the behavior of deep reinforcement learning models globally.

Findings

Provides global explanations for RL decisions

Captures intuitive tendencies of models

Enhances interpretability of deep RL models

Abstract

Artificial intelligence, particularly through recent advancements in deep learning, has achieved exceptional performances in many tasks in fields such as natural language processing and computer vision. In addition to desirable evaluation metrics, a high level of interpretability is often required for these models to be reliably utilized. Therefore, explanations that offer insight into the process by which a model maps its inputs onto its outputs are much sought-after. Unfortunately, the current black box nature of machine learning models is still an unresolved issue and this very nature prevents researchers from learning and providing explicative descriptions for a model's behavior and final predictions. In this work, we propose a novel framework utilizing Adversarial Inverse Reinforcement Learning that can provide global explanations for decisions made by a Reinforcement Learning model and capture intuitive tendencies that the model follows by summarizing the model's decision-making process.