An AI Chatbot for Explaining Deep Reinforcement Learning Decisions of Service-oriented Systems

TL;DR

This paper presents Chat4XAI, an AI chatbot-based system that provides natural-language explanations for deep reinforcement learning decisions in service-oriented systems, enhancing understandability and trust.

Contribution

It introduces Chat4XAI, a novel approach leveraging AI chatbot technology for explaining Deep RL decisions without predefined question-answer pairs.

Findings

Chat4XAI improves explanation fidelity and stability.

Natural-language explanations increase user trust.

The system effectively explains Deep RL in service contexts.

Abstract

Deep Reinforcement Learning (Deep RL) is increasingly used to cope with the open-world assumption in service-oriented systems. Deep RL was successfully applied to problems such as dynamic service composition, job scheduling, and offloading, as well as service adaptation. While Deep RL offers many benefits, understanding the decision-making of Deep RL is challenging because its learned decision-making policy essentially appears as a black box. Yet, understanding the decision-making of Deep RL is key to help service developers perform debugging, support service providers to comply with relevant legal frameworks, and facilitate service users to build trust. We introduce Chat4XAI to facilitate the understanding of the decision-making of Deep RL by providing natural-language explanations. Compared with visual explanations, the reported benefits of natural-language explanations include better understandability for non-technical users, increased user acceptance and trust, as well as more efficient explanations. Chat4XAI leverages modern AI chatbot technology and dedicated prompt engineering. Compared to earlier work on natural-language explanations using classical software-based dialogue systems, using an AI chatbot eliminates the need for eliciting and defining potential questions and answers up-front. We prototypically realize Chat4XAI using OpenAI's ChatGPT API and evaluate the fidelity and stability of its explanations using an adaptive service exemplar.