# Model-Free Model Reconciliation

## TL;DR

This paper extends the model-reconciliation explanation framework to scenarios lacking explicit user models by introducing a learnable labeling model to identify helpful information for aligning user and agent models.

## Contribution

It proposes a simple, learnable labeling approach to facilitate model reconciliation without requiring explicit user models, broadening the applicability of explanation methods.

## Key findings

- The labeling model effectively identifies information to reconcile user and agent models.
- The approach simplifies the process of generating explanations in complex decision-making.
- It demonstrates potential for improved agent-user communication in AI systems.

## Abstract

Designing agents capable of explaining complex sequential decisions remain a significant open problem in automated decision-making. Recently, there has been a lot of interest in developing approaches for generating such explanations for various decision-making paradigms. One such approach has been the idea of {\em explanation as model-reconciliation}. The framework hypothesizes that one of the common reasons for the user's confusion could be the mismatch between the user's model of the task and the one used by the system to generate the decisions. While this is a general framework, most works that have been explicitly built on this explanatory philosophy have focused on settings where the model of user's knowledge is available in a declarative form. Our goal in this paper is to adapt the model reconciliation approach to the cases where such user models are no longer explicitly provided. We present a simple and easy to learn labeling model that can help an explainer decide what information could help achieve model reconciliation between the user and the agent.