Learning "What-if" Explanations for Sequential Decision-Making

TL;DR

This paper introduces a method to interpret expert decision-making by modeling their reward functions through counterfactual reasoning, enabling explanations of actions in sequential settings without active experimentation.

Contribution

It proposes a novel batch inverse reinforcement learning approach that incorporates counterfactuals to explain expert behavior in sequential decision-making tasks.

Findings

Effective in real and simulated medical environments

Accurately recovers interpretable behavior descriptions

Handles off-policy evaluation with counterfactual reasoning

Abstract

Building interpretable parameterizations of real-world decision-making on the basis of demonstrated behavior -- i.e. trajectories of observations and actions made by an expert maximizing some unknown reward function -- is essential for introspecting and auditing policies in different institutions. In this paper, we propose learning explanations of expert decisions by modeling their reward function in terms of preferences with respect to "what if" outcomes: Given the current history of observations, what would happen if we took a particular action? To learn these cost-benefit tradeoffs associated with the expert's actions, we integrate counterfactual reasoning into batch inverse reinforcement learning. This offers a principled way of defining reward functions and explaining expert behavior, and also satisfies the constraints of real-world decision-making -- where active experimentation is often impossible (e.g. in healthcare). Additionally, by estimating the effects of different actions, counterfactuals readily tackle the off-policy nature of policy evaluation in the batch setting, and can naturally accommodate settings where the expert policies depend on histories of observations rather than just current states. Through illustrative experiments in both real and simulated medical environments, we highlight the effectiveness of our batch, counterfactual inverse reinforcement learning approach in recovering accurate and interpretable descriptions of behavior.