What Matters in Hierarchical Search for Combinatorial Reasoning Problems?
Published in ICLR 2024 (Generative Models for Decision Making), 2024
This work studies when hierarchical search is useful for combinatorial reasoning problems. It focuses on environments with difficult value functions, complex action spaces, dead ends, or heterogeneous training data.
The paper reports controlled empirical comparisons and proposes evaluation guidelines for future hierarchical planning methods.
Links:
Recommended citation: Zawalski, M., Góral, G., Tyrolski, M., Wiśnios, E., Budrowski, F., Cygan, M., Kuciński, Ł., & Miłoś, P. (2024). What matters in hierarchical search for combinatorial reasoning problems? arXiv preprint arXiv:2406.03361.
Download Paper | Download Slides