Interactive Explanations: Diagnosis and Repair of Reinforcement Learning Based Agent Behaviors

TL;DR

This paper introduces an interactive explanation method for reinforcement learning agents that enables transparent communication and user-guided behavior repair through natural language templates, demonstrated in a Super Mario Bros. clone.

Contribution

It presents a novel two-way interaction approach using natural language templates for explaining and repairing reinforcement learning agent behaviors.

Findings

Effective diagnosis of agent behaviors

Successful repair of behaviors via user feedback

Enhanced transparency of agent decision-making

Abstract

Reinforcement learning techniques successfully generate convincing agent behaviors, but it is still difficult to tailor the behavior to align with a user's specific preferences. What is missing is a communication method for the system to explain the behavior and for the user to repair it. In this paper, we present a novel interaction method that uses interactive explanations using templates of natural language as a communication method. The main advantage of this interaction method is that it enables a two-way communication channel between users and the agent; the bot can explain its thinking procedure to the users, and the users can communicate their behavior preferences to the bot using the same interactive explanations. In this manner, the thinking procedure of the bot is transparent, and users can provide corrections to the bot that include a suggested action to take, a goal to achieve, and the reasons behind these decisions. We tested our proposed method in a clone of the video game named \textit{Super Mario Bros.}, and the results demonstrate that our interactive explanation approach is effective at diagnosing and repairing bot behaviors.