TY - JOUR AU - Shen, William AU - Trevizan, Felipe AU - Thiébaux, Sylvie PY - 2020/06/01 Y2 - 2024/03/28 TI - Learning Domain-Independent Planning Heuristics with Hypergraph Networks JF - Proceedings of the International Conference on Automated Planning and Scheduling JA - ICAPS VL - 30 IS - 1 SE - Planning and Learning DO - 10.1609/icaps.v30i1.6754 UR - https://ojs.aaai.org/index.php/ICAPS/article/view/6754 SP - 574-584 AB - <p>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.</p> ER -