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.

  • News and Highlights
    • STRIPS-HGN: First algorithm capable of learning domain-independent heuristics from scratch (ICAPS'20).
    • New insights and results for ASNets on arXiv (still under review)
    • Guiding search using generalized policies from ASNets (SoCS'19)
    • PLTL-dual: First heuristic search algorithm for SSPs and MDPs with Probabilistic LTL constraints (KR'18).
    • ASNets: Learning generalized policies for SSPs using neural nets (AAAI'18).
    • h-pom, h-roc, and i2-dual won the best paper award at ICAPS'17!
    • New efficient approach to solve SSPs and C-SSPs with dead ends (UAI'17).
    • h-pom and h-roc: the first heuristics able to handle probabilities and costs for SSPs and C-SSPs (ICAPS'17).
    • i-dual won the best paper award at ICAPS'16!
    • QTM won the Kikuchi-Karlaftis best paper award at TRB'16! (demo).
  • Word cloud of my papers
  • wordcloud
    large wordcloud