Structurally Guided Task Decomposition in Spatial Navigation Tasks (Student Abstract)

Authors

  • Ruiqi He Max Planck Institute for Intelligent Systems, Tübingen
  • Carlos G. Correa Princeton Neuroscience Institute, Princeton University, Princeton, New Jersey
  • Tom L. Griffiths Department of Psychology, Princeton University, Princeton, New Jersey Department of Computer Science, Princeton University, Princeton, New Jersey
  • Mark K. Ho Department of Computer Science, Stevens Institute of Technology, Hoboken, New Jersey

DOI:

https://doi.org/10.1609/aaai.v38i21.30451

Keywords:

Planning, Task Decomposition, Hierarchical Reinforcement Learning, Options, Spatial Navigation

Abstract

How are people able to plan so efficiently despite limited cognitive resources? We aimed to answer this question by extending an existing model of human task decomposition that can explain a wide range of simple planning problems by adding structure information to the task to facilitate planning in more complex tasks. The extended model was then applied to a more complex planning domain of spatial navigation. Our results suggest that our framework can correctly predict the navigation strategies of the majority of the participants in an online experiment.
AAAI-24 / IAAI-24 / EAAI-24 Proceedings Cover

Downloads

Published

2024-03-24

How to Cite

He, R., Correa, C. G., Griffiths, T. L., & Ho, M. K. (2024). Structurally Guided Task Decomposition in Spatial Navigation Tasks (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 23512–23513. https://doi.org/10.1609/aaai.v38i21.30451

Issue

Vol. 38 No. 21: IAAI-24, EAAI-24, AAAI-24 Student Abstracts, Undergraduate Consortium and Demonstrations

Section

AAAI Student Abstract and Poster Program