Return to Tradition: Learning Reliable Heuristics with Classical Machine Learning
This work addresses the challenge of improving planning performance for AI systems by developing a more efficient and reliable learning approach, though it is incremental as it builds on existing classical methods.
The paper tackles the problem of learning heuristics for planning by constructing novel graph representations and using the WL algorithm to generate features, combined with classical machine learning methods, resulting in up to 2 orders of magnitude fewer parameters and 3 orders of magnitude faster training than deep learning models, while outperforming or tying with LAMA on coverage and plan quality in multiple domains.
Current approaches for learning for planning have yet to achieve competitive performance against classical planners in several domains, and have poor overall performance. In this work, we construct novel graph representations of lifted planning tasks and use the WL algorithm to generate features from them. These features are used with classical machine learning methods which have up to 2 orders of magnitude fewer parameters and train up to 3 orders of magnitude faster than the state-of-the-art deep learning for planning models. Our novel approach, WL-GOOSE, reliably learns heuristics from scratch and outperforms the $h^{\text{FF}}$ heuristic in a fair competition setting. It also outperforms or ties with LAMA on 4 out of 10 domains on coverage and 7 out of 10 domains on plan quality. WL-GOOSE is the first learning for planning model which achieves these feats. Furthermore, we study the connections between our novel WL feature generation method, previous theoretically flavoured learning architectures, and Description Logic Features for planning.