Graph Neural Network Based Action Ranking for Planning

We propose a novel approach to learn relational policies for classical planning based on learning to rank actions. We introduce a new graph representation that explicitly captures action information and propose a Graph Neural Network (GNN) architecture augmented with Gated Recurrent Units (GRUs) to learn action rankings. Unlike value-function based approaches that must learn a globally consistent function, our action ranking method only needs to learn locally consistent ranking. Our model is trained on data generated from small problem instances that are easily solved by planners and is applied to significantly larger instances where planning is computationally prohibitive. Experimental results across standard planning benchmarks demonstrate that our action-ranking approach not only achieves better generalization to larger problems than those used in training but also outperforms multiple baselines (value function and action ranking) methods in terms of success rate and plan quality. Recently, several neural approaches have been proposed in the planning domain. Some methods learn value functions to guide search processes [22, 1] , while others learn value functions that induce greedy policies by selecting actions leading to states with minimum estimated cost-to-go [24, 23] . 39th Conference on Neural Information Processing Systems (NeurIPS 2025).