---
title: "Continuous Multi-Attribute Recognition for Agent Behaviour Understanding"
authors:
  - "Sheryl Mantik"
  - "Michael Dann"
  - "Huong Ha"
  - "Minyi Li"
  - "Julie Porteous"
doi: "10.24963/ijcai.2026/28"
url: "https://ijcai.org/proceedings/2026/28"
pdf: "https://ijcai.org/proceedings/2026/0028.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "244-252"
track: "Main Track"
keywords:
  - "Agent-based and Multi-agent Systems: Agent theories and models"
  - "Knowledge Representation and Reasoning: Reasoning about actions"
  - "Machine Learning: Reinforcement learning"
  - "Planning and Scheduling: Activity and plan recognition"
---

# Continuous Multi-Attribute Recognition for Agent Behaviour Understanding

Sheryl Mantik, Michael Dann, Huong Ha, Minyi Li, Julie Porteous

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 244-252. DOI: [10.24963/ijcai.2026/28](https://doi.org/10.24963/ijcai.2026/28)

## Abstract

Understanding underlying agent attributes such as goals, preferences, beliefs, and ability level is key to explaining decision-making and predicting behaviour in complex environments. While goal recognition (GR) has produced effective methods for inferring goals, recent work has begun to explore reinforcement learning (RL)-based approaches to attribute recognition (AR), which generalises GR by inferring a wider range of agent attributes beyond goals. Existing frameworks treat attributes as discrete variables and typically require separate models for each attribute. In reality, many agent attributes vary continuously rather than as discrete values, making continuous representations crucial for capturing subtle variations in behaviour. We introduce a multivariate RL-based AR framework that jointly infers multiple continuous-valued attributes from observed behaviour using a single attribute-conditioned policy and continuous probabilistic inference. Our experiments demonstrate that the proposed framework achieves stable and fine-grained inference, offering improved flexibility and generality compared to existing approaches.