Learning Domain-Independent Planning Heuristics with Hypergraph Networks

Abstract

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.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Neural Message Passing for Quantum Chemistry
• The 3rd International Planning Competition: Results and Analysis
• Action Schema Networks: Generalised Policies with Deep Learning
• Towards learning domain-independent planning heuristics
• Size Independent Neural Transfer for RDDL Planning

Cited by in corpus (3)

• Generalized Planning With Deep Reinforcement Learning
• ASNets: Deep Learning for Generalised Planning
• Learning Domain-Independent Heuristics for Grounded and Lifted Planning