Explainable Reinforcement Learning Agents Using World Models

Explainable AI (XAI) systems have been proposed to help people understand how AI systems produce outputs and behaviors. Explainable Reinforcement Learning (XRL) has an added complexity due to the temporal nature of sequential decision-making. Further, non-AI experts do not necessarily have the ability to alter an agent or its policy. We introduce a technique for using World Models to generate explanations for Model-Based Deep RL agents. World Models predict how the world will change when actions are performed, allowing for the generation of counterfactual trajectories. However, identifying what a user wanted the agent to do is not enough to understand why the agent did something else. We augment Model-Based RL agents with a Reverse World Model, which predicts what the state of the world should have been for the agent to prefer a given counterfactual action. We show that explanations that show users what the world should have been like significantly increase their understanding of the agent policy. We hypothesize that our explanations can help users learn how to control the agents execution through by manipulating the environment.

Why Don't You Do Something About It? Outlining Connections between AI Explanations and User Actions

A core assumption of explainable AI systems is that explanations change what users know, thereby enabling them to act within their complex socio-technical environments. Despite the centrality of action, explanations are often organized and evaluated based on technical aspects. Prior work varies widely in the connections it traces between information provided in explanations and resulting user actions. An important first step in centering action in evaluations is understanding what the XAI community collectively recognizes as the range of information that explanations can present and what actions are associated with them. In this paper, we present our framework, which maps prior work on information presented in explanations and user action, and we discuss the gaps we uncovered about the information presented to users.