Goal Recognition Design for General Behavioral Agents using Machine Learning

TL;DR

This paper introduces a machine learning-based framework for goal recognition design that improves efficiency and applicability in complex, suboptimal, and human-involved environments by optimizing decision-making settings.

Contribution

It presents a novel gradient-based optimization approach leveraging machine learning to enhance goal recognition in diverse and complex environments, surpassing prior computationally demanding methods.

Findings

Outperforms existing methods in reducing worst-case distinctiveness (wcd).

Improves runtime efficiency in goal recognition tasks.

Adapts to complex, flexible, and human-involved environments.

Abstract

Goal recognition design (GRD) aims to make limited modifications to decision-making environments to make it easier to infer the goals of agents acting within those environments. Although various research efforts have been made in goal recognition design, existing approaches are computationally demanding and often assume that agents are (near-)optimal in their decision-making. To address these limitations, we leverage machine learning methods for goal recognition design that can both improve run-time efficiency and account for agents with general behavioral models. Following existing literature, we use worst-case distinctiveness (wcd) as a measure of the difficulty in inferring the goal of an agent in a decision-making environment. Our approach begins by training a machine learning model to predict the wcd for a given environment and the agent behavior model. We then propose a gradient-based optimization framework that accommodates various constraints to optimize decision-making environments for enhanced goal recognition. Through extensive simulations, we demonstrate that our approach outperforms existing methods in reducing wcd and enhances runtime efficiency. Moreover, our approach also adapts to settings in which existing approaches do not apply, such as those involving flexible budget constraints, more complex environments, and suboptimal agent behavior. Finally, we conducted human-subject experiments that demonstrate that our method creates environments that facilitate efficient goal recognition from human decision-makers.