Probabilistic Active Goal Recognition

2025-07-29

AI Summary

This paper addresses the problem of actively inferring other agents’ hidden goals in multi-agent settings where no prior domain knowledge is available. Methodologically, it introduces the first domain-agnostic active goal recognition framework, built upon a joint belief-updating probabilistic inference model and a domain-knowledge-free Monte Carlo Tree Search (MCTS) algorithm that jointly optimizes information-gathering policies and goal inference. Its core contribution lies in formalizing active perception as a sequential decision-making problem—eliminating reliance on expert-designed heuristics or environment-specific assumptions. Empirical evaluation in grid-world environments demonstrates that the approach significantly improves goal recognition accuracy—achieving over 40% higher accuracy than passive baselines—while matching the performance of strong domain-specific greedy policies. These results validate both the framework’s effectiveness and its generalizability across diverse domains.

Technology Category

• Machine Learning: Active Learning
• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

In multi-agent environments, effective interaction hinges on understanding the beliefs and intentions of other agents. While prior work on goal recognition has largely treated the observer as a passive reasoner, Active Goal Recognition (AGR) focuses on strategically gathering information to reduce uncertainty. We adopt a probabilistic framework for Active Goal Recognition and propose an integrated solution that combines a joint belief update mechanism with a Monte Carlo Tree Search (MCTS) algorithm, allowing the observer to plan efficiently and infer the actor's hidden goal without requiring domain-specific knowledge. Through comprehensive empirical evaluation in a grid-based domain, we show that our joint belief update significantly outperforms passive goal recognition, and that our domain-independent MCTS performs comparably to our strong domain-specific greedy baseline. These results establish our solution as a practical and robust framework for goal inference, advancing the field toward more interactive and adaptive multi-agent systems.

Problem

• Understand agents' beliefs and intentions in multi-agent environments
• Reduce uncertainty by actively gathering information for goal recognition
• Infer hidden goals without domain-specific knowledge using probabilistic methods

Innovation

• Probabilistic framework for Active Goal Recognition
• Joint belief update mechanism with MCTS
• Domain-independent efficient planning and inference