Explainability Insights to Cellular Simultaneous Recurrent Neural Networks for Classical Planning

Michaela Urbanovská, Antonín Komenda

2024

Abstract

The connection between symbolic artificial intelligence and statistical machine learning has been explored in many ways. That includes using machine learning to learn new heuristic functions for navigating classical planning algorithms. Many approaches which target this task use different problem representations and different machine learning techniques to train estimators for navigating search algorithms to find sequential solutions to deterministic problems. In this work, we focus on one of these approaches which is the semantically layered Cellular Simultaneous Neural Network architecture (slCSRN) (Urbanovská and Komenda, 2023) used to learn heuristic for grid-based planning problems represented by the semantically layered representation. We create new problem domains for this architecture - the Tetris and Rush-Hour domains. Both do not have an explicit agent that only modifies its surroundings unlike already explored problem domains. We compare the performance of the trained slCSRN to the existing classical planning heuristics and we also provide insights into the slCSRN computation as we provide explainability analysis of the learned heuristic functions.

Paper Citation

in Harvard Style

Urbanovská M. and Komenda A. (2024). Explainability Insights to Cellular Simultaneous Recurrent Neural Networks for Classical Planning. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 592-599. DOI: 10.5220/0012375800003636

in Bibtex Style

@conference{icaart24,
author={Michaela Urbanovská and Antonín Komenda},
title={Explainability Insights to Cellular Simultaneous Recurrent Neural Networks for Classical Planning},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={592-599},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012375800003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Explainability Insights to Cellular Simultaneous Recurrent Neural Networks for Classical Planning
SN - 978-989-758-680-4
AU - Urbanovská M.
AU - Komenda A.
PY - 2024
SP - 592
EP - 599
DO - 10.5220/0012375800003636
PB - SciTePress