Inferring Agents Preferences as Priors for Probabilistic Goal Recognition

TL;DR

This paper introduces a probabilistic model for goal recognition that extends landmark-based methods by estimating and utilizing prior preferences, improving goal inference accuracy through repeated observations.

Contribution

It provides a novel probabilistic interpretation for landmark-based goal recognition and enables the estimation and use of prior preferences in the process.

Findings

Effective goal recognition demonstrated

Successful inference of agent preferences

Improved accuracy with repeated observations

Abstract

Recent approaches to goal recognition have leveraged planning landmarks to achieve high-accuracy with low runtime cost. These approaches, however, lack a probabilistic interpretation. Furthermore, while most probabilistic models to goal recognition assume that the recognizer has access to a prior probability representing, for example, an agent's preferences, virtually no goal recognition approach actually uses the prior in practice, simply assuming a uniform prior. In this paper, we provide a model to both extend landmark-based goal recognition with a probabilistic interpretation and allow the estimation of such prior probability and its usage to compute posterior probabilities after repeated interactions of observed agents. We empirically show that our model can not only recognize goals effectively but also successfully infer the correct prior probability distribution representing an agent's preferences.