Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning

arXiv:2605.18674v1 Announce Type: new Abstract: Generalized planning aims to learn policies that generalize across collections of instances within a classical planning domain. Recent Graph Neural Network (GNN) approaches have learned nearly perfect policies for several domains. This work improves on the recently published idea of Iterated Width (IW) policies. Therein, the policy broadens its successor scope through an IW-lookahead search that can "jump" over multiple transitions, simplifying the