---
title: "What’s the Context? Implicit and Explicit Assumptions in Model-Based Goal Recognition"
authors:
  - "Peta Masters"
  - "Mor Vered"
doi: "10.24963/ijcai.2021/615"
url: "https://ijcai.org/proceedings/2021/615"
pdf: "https://ijcai.org/proceedings/2021/0615.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "4516-4523"
track: "Survey Track"
keywords:
  - "Agent-based and multi-agent based systems: General"
  - "Humans and AI: General"
  - "Planning and scheduling: General"
---

# What’s the Context? Implicit and Explicit Assumptions in Model-Based Goal Recognition

Peta Masters, Mor Vered

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 4516-4523. DOI: [10.24963/ijcai.2021/615](https://doi.org/10.24963/ijcai.2021/615)

## Abstract

Every model involves assumptions. While some are standard to all models that simulate intelligent decision-making (e.g., discrete/continuous, static/dynamic), goal recognition is well known also to involve choices about the observed agent: is it aware of being observed? cooperative or adversarial? In this paper, we examine not only these but the many other assumptions made in the context of model-based goal recognition. By exploring their meaning, the relationships between them and the confusions that can arise, we demonstrate their importance, shed light on the way trends emerge in AI, and suggest a novel means for researchers to uncover suitable avenues for future work.