Continuous Multi-Attribute Recognition for Agent Behaviour Understanding

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

IJCAI 20260 citations

Continuous Multi-Attribute Recognition for Agent Behaviour Understanding

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

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.

Agent-based and Multi-agent Systems: Agent theories and modelsKnowledge Representation and Reasoning: Reasoning about actionsMachine Learning: Reinforcement learningPlanning and Scheduling: Activity and plan recognition

BibTeX

@inproceedings{ijcai2026_continuousmultia,
  title = {Continuous Multi-Attribute Recognition for Agent Behaviour Understanding},
  author = {Sheryl Mantik and Michael Dann and Huong Ha and Minyi Li and Julie Porteous},
  booktitle = {IJCAI 2026},
  year = {2026}
}