Learning Generalized Relational Heuristic Networks for Model-Agnostic Planning
Keywords:Transfer/Adaptation/Multi-task/Meta/Automated Learning, Planning/Scheduling and Learning, Relational Learning
AbstractComputing 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.
How to Cite
Karia, R., & Srivastava, S. (2021). Learning Generalized Relational Heuristic Networks for Model-Agnostic Planning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(9), 8064-8073. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16983
AAAI Technical Track on Machine Learning II