Learning Planning Heuristics with Hypergraph Networks
Shen, W., Trevizan, F. and Thiébaux, S.
To appear in Proc. of 30th Int. Conf. on Automated Planning and Scheduling (ICAPS).
We are working on the camera-ready of this paper and it will be available soon.
Bellow is the abstract of this paper.
We present the first approach capable of learning domain-independent
planning heuristics entirely from scratch. The heuristics we learn map the
hypergraph representation of the delete-relaxation of the planning problem
at hand, to a cost estimate that approximates that of the least-cost path
from the current state to the goal through the hypergraph. We generalise
Graph Networks to obtain a new framework for learning over hypergraphs,
which we specialise to learn planning heuristics by training over
state/value pairs obtained from optimal cost plans. Our experiments show
that the resulting architecture, STRIPS-HGNs, is capable of learning
heuristics that are competitive with existing delete-relaxation heuristics
including LM-cut. We show that the heuristics we learn are able to
generalise across different problems and domains, including to domains that
were not seen during training.