A longstanding objective in classical planning is to synthesize policies that
generalize across multiple problems from the same domain. In this work, we
study generalized policy search-based methods with a focus on the score
function used to guide the search over policies. We demonstrate limitations of
two score functions and propose a new approach that overcomes these
limitations. The main idea behind our approach, Policy-Guided Planning for
Generalized Policy Generation (PG3), is that a candidate policy should be used
to guide planning on training problems as a mechanism for evaluating that
candidate. Theoretical results in a simplified setting give conditions under
which PG3 is optimal or admissible. We then study a specific instantiation of
policy search where planning problems are PDDL-based and policies are lifted
decision lists. Empirical results in six domains confirm that PG3 learns
generalized policies more efficiently and effectively than several baselines.
Code: this https URL

本论文关注基于广义策略搜索的方法，提出了 Score function 的限制，并提出了能够克服这些限制的 Policy-Guided Planning for Generalized Policy Generation (PG3)，该论文在六种不同的领域进行实验，结果证明 PG3 比其他基线更有效地学习了泛化策略。