Goal Recognition as Reinforcement Learning

Leonardo Rosa Amado, Reuth Mirsky, Felipe Meneguzzi

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution


Most approaches for goal recognition rely on specifications of the possible dynamics of the actor in the environment when pursuing a goal. These specifications suffer from two key issues. First, encoding these dynamics requires careful design by a domain expert, which is often not robust to noise at recognition time. Second, existing approaches often need costly real-time computations to reason about the likelihood of each potential goal. In this paper, we develop a framework that combines model-free reinforcement learning and goal recognition to alleviate the need for careful, manual domain design, and the need for costly online executions. This framework consists of two main stages: Offline learning of policies or utility functions for each potential goal, and online inference. We provide a first instance of this framework using tabular Q-learning for the learning stage, as well as three measures that can be used to perform the inference stage. The resulting instantiation achieves state-of-the-art performance against goal recognizers on standard evaluation domains and superior performance in noisy environments.
Original languageEnglish
Title of host publicationProceedings of the AAAI Conference on Artificial Intelligence
Place of PublicationPalo Alto, California
PublisherAAAI Press
Number of pages8
ISBN (Electronic)2374-3468
ISBN (Print)2159-5399
Publication statusPublished - 30 Jun 2022
EventThirty-Sixth AAAI Conference on Artificial Intelligence - Vancouver, Canada
Duration: 22 Feb 20221 Mar 2022
Conference number: 36


ConferenceThirty-Sixth AAAI Conference on Artificial Intelligence
Abbreviated titleAAAI-22
Internet address


  • cs.AI
  • cs.LG
  • Planning, Routing, And Scheduling (PRS)
  • Multiagent Systems (MAS)
  • Machine Learning (ML)


Dive into the research topics of 'Goal Recognition as Reinforcement Learning'. Together they form a unique fingerprint.

Cite this