@article{Francès_Bonet_Geffner_2021, title={Learning General Planning Policies from Small Examples Without Supervision}, volume={35}, url={https://ojs.aaai.org/index.php/AAAI/article/view/17402}, DOI={10.1609/aaai.v35i13.17402}, abstractNote={Generalized planning is concerned with the computation of general policies that solve multiple instances of a planning domain all at once. It has been recently shown that these policies can be computed in two steps: first, a suitable abstraction in the form of a qualitative numerical planning problem (QNP) is learned from sample plans, then the general policies are obtained from the learned QNP using a planner. In this work, we introduce an alternative approach for computing more expressive general policies which does not require sample plans or a QNP planner. The new formulation is very simple and can be cast in terms that are more standard in machine learning: a large but finite pool of features is defined from the predicates in the planning examples using a general grammar, and a small subset of features is sought for separating “good” from “bad” state transitions, and goals from non-goals. The problems of finding such a “separating surface” while labeling the transitions as “good” or “bad” are jointly addressed as a single combinatorial optimization problem expressed as a Weighted Max-SAT problem. The advantage of looking for the simplest policy in the given feature space that solves the given examples, possibly non-optimally, is that many domains have no general, compact policies that are optimal. The approach yields general policies for a number of benchmark domains.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Francès, Guillem and Bonet, Blai and Geffner, Hector}, year={2021}, month={May}, pages={11801-11808} }