Neural Network Heuristic Functions for Classical Planning: Bootstrapping and Comparison to Other Methods

Ferber, Patrick and Geißer, Florian and Trevizan, Felipe and Helmert, Malte and Hoffmann, Jörg. (2022) Neural Network Heuristic Functions for Classical Planning: Bootstrapping and Comparison to Other Methods. In: Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling (ICAPS 2022). pp. 583-587.

[img] PDF - Accepted Version

Official URL: https://edoc.unibas.ch/93507/

Downloads: Statistics Overview


How can we train neural network (NN) heuristic functions for classical planning, using only states as the NN input? Prior work addressed this question by (a) per-instance imitation learning and/or (b) per-domain learning. The former limits the approach to instances small enough for training data generation, the latter to domains where the necessary knowledge generalizes across instances. Here we explore three methods for (a) that make training data generation scalable through bootstrapping and approximate value iteration. In particular, we introduce a new bootstrapping variant that estimates search effort instead of goal distance, which as we show converges to the perfect heuristic under idealized circumstances. We empirically compare these methods to (a) and (b), aligning three different NN heuristic function learning architectures for cross-comparison in an experiment of unprecedented breadth in this context. Key lessons are that our methods and imitation learning are highly complementary; that per-instance learning often yields stronger heuristics than per-domain learning; and the LAMA planner is still dominant but our methods outperform it in one benchmark domain.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Artificial Intelligence (Helmert)
UniBasel Contributors:Ferber, Patrick and Helmert, Malte
Item Type:Conference or Workshop Item, refereed
Conference or workshop item Subtype:Conference Paper
Publisher:AAAI Press
Note:Publication type according to Uni Basel Research Database: Conference paper
Identification Number:
edoc DOI:
Last Modified:29 Mar 2023 12:29
Deposited On:15 Feb 2023 11:12

Repository Staff Only: item control page