Abstract
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 language | English |
---|---|
Title of host publication | Proceedings of the 36th AAAI Conference on Artificial Intelligence Vol. 36 No 9 |
Subtitle of host publication | AAAI-22 Technical Tracks 9 |
Place of Publication | Palo Alto, California |
Publisher | AAAI Press |
Pages | 9644-9651 |
Number of pages | 8 |
Volume | 36 |
Edition | 9 |
ISBN (Print) | 978-1-57735-876-3 |
DOIs | |
Publication status | Published - 30 Jun 2022 |
Event | Thirty-Sixth AAAI Conference on Artificial Intelligence - Vancouver, Canada Duration: 22 Feb 2022 → 1 Mar 2022 Conference number: 36 https://aaai.org/Conferences/AAAI-22/ |
Publication series
Name | Proceedings of the AAAI Conference on Artificial Intelligence |
---|---|
Publisher | AAAI Press |
ISSN (Print) | 2159-5399 |
ISSN (Electronic) | 2374-3468 |
Conference
Conference | Thirty-Sixth AAAI Conference on Artificial Intelligence |
---|---|
Abbreviated title | AAAI-22 |
Country/Territory | Canada |
City | Vancouver |
Period | 22/02/22 → 1/03/22 |
Internet address |
Keywords
- cs.AI
- cs.LG
- Planning, Routing, And Scheduling (PRS)
- Multiagent Systems (MAS)
- Machine Learning (ML)