Learning Domain-Independent Planning Heuristics with Hypergraph Networks
This addresses the challenge of automated planning for AI systems, offering a novel learning-based approach that is incremental in improving heuristic generalization.
The authors tackled the problem of learning domain-independent planning heuristics from scratch, resulting in STRIPS-HGNs, which are competitive with existing methods like LM-cut and can generalize to unseen domains.
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.