TY - GEN
T1 - Guiding GBFS through Learned Pairwise Rankings
AU - Hao, Mingyu
AU - Trevizan, Felipe
AU - Thiébaux, Sylvie
AU - Ferber, Patrick
AU - Hoffmann, Jörg
N1 - Publisher Copyright:
© 2024 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2024
Y1 - 2024
N2 - We propose a new approach based on ranking to learn to guide Greedy Best-First Search (GBFS). As previous ranking approaches, ours is based on the observation that directly learning a heuristic function is overly restrictive, and that GBFS is capable of efficiently finding good plans for a much more flexible class of total quasi-orders over states. In order to learn an optimal ranking function, we introduce a new ranking framework capable of leveraging any neural network regression model and efficiently handling the training data through batching. Compared with previous ranking approaches for planning, ours does not require complex loss functions and allows training on states outside the optimal plan with minimal overhead. Our experiments on the domains of the latest planning competition learning track show that our approach substantially improves the coverage of the underlying neural network models without degrading plan quality.
AB - We propose a new approach based on ranking to learn to guide Greedy Best-First Search (GBFS). As previous ranking approaches, ours is based on the observation that directly learning a heuristic function is overly restrictive, and that GBFS is capable of efficiently finding good plans for a much more flexible class of total quasi-orders over states. In order to learn an optimal ranking function, we introduce a new ranking framework capable of leveraging any neural network regression model and efficiently handling the training data through batching. Compared with previous ranking approaches for planning, ours does not require complex loss functions and allows training on states outside the optimal plan with minimal overhead. Our experiments on the domains of the latest planning competition learning track show that our approach substantially improves the coverage of the underlying neural network models without degrading plan quality.
UR - http://www.scopus.com/inward/record.url?scp=85204287052&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85204287052
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 6724
EP - 6732
BT - Proceedings of the 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024
A2 - Larson, Kate
PB - International Joint Conferences on Artificial Intelligence
T2 - 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024
Y2 - 3 August 2024 through 9 August 2024
ER -