TY - GEN
T1 - Learning Generalized Relational Heuristic Networks for Model-Agnostic Planning
AU - Karia, Rushang
AU - Srivastava, Siddharth
N1 - Funding Information:
We thank Julia Nakhleh for help with a prototype implementation of the source code. We thank the Research Computing group at Arizona State University for providing compute hours for our experiments. This research was supported in part by the NSF under grants IIS 1942856 and IIS 1909370.
Publisher Copyright:
Copyright © 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved
PY - 2021
Y1 - 2021
N2 - Computing goal-directed behavior is essential to designing efficient AI systems. Due to the computational complexity of planning, current approaches rely primarily upon hand-coded symbolic action models and hand-coded heuristic function generators for efficiency. Learned heuristics for such problems have been of limited utility as they are difficult to apply to problems with objects and object quantities that are significantly different from those in the training data. This paper develops a new approach for learning generalized heuristics in the absence of symbolic action models using deep neural networks that utilize an input predicate vocabulary but are agnostic to object names and quantities. It uses an abstract state representation to facilitate data-efficient, generalizable learning. Empirical evaluation on a range of benchmark domains shows that in contrast to prior approaches, generalized heuristics computed by this method can be transferred easily to problems with different objects and with object quantities much larger than those in the training data.
AB - Computing goal-directed behavior is essential to designing efficient AI systems. Due to the computational complexity of planning, current approaches rely primarily upon hand-coded symbolic action models and hand-coded heuristic function generators for efficiency. Learned heuristics for such problems have been of limited utility as they are difficult to apply to problems with objects and object quantities that are significantly different from those in the training data. This paper develops a new approach for learning generalized heuristics in the absence of symbolic action models using deep neural networks that utilize an input predicate vocabulary but are agnostic to object names and quantities. It uses an abstract state representation to facilitate data-efficient, generalizable learning. Empirical evaluation on a range of benchmark domains shows that in contrast to prior approaches, generalized heuristics computed by this method can be transferred easily to problems with different objects and with object quantities much larger than those in the training data.
UR - http://www.scopus.com/inward/record.url?scp=85130092775&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85130092775&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85130092775
T3 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
SP - 8064
EP - 8073
BT - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
PB - Association for the Advancement of Artificial Intelligence
T2 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
Y2 - 2 February 2021 through 9 February 2021
ER -