Graph Learning for Planning
State of the art methods for automated planning rely on heuristic state-space search. I will present recent work on graph representation learning to guide the search of automated planners. I will introduce graph neural network and other graph learning representations that exploit the relational structure of planning domains. They allow our planner GOOSE to learn heuristic cost estimates and state rankings from solutions to just a few small problems, and solve substantially larger problems than trained on. Perhaps surprisingly, our experimental results show that classical machine learning approaches vastly outperform deep learning ones in this context. Moreover, Greedy Best-First Search guided by our best learnt heuristics rivals with the state of the art model-based planner, Lama, on the problems of the latest International Planning Competition Learning track, leading to the possibility that learnt heuristics may replace existing model-based heuristics in the near future.