Automated planning instance generation with neuro-symbolic AI

Artificial Intelligence, vol. 352, pp. 104471

Abstract

• A neuro-symbolic generative model for Automated Planning problems is proposed. • Our method generates valid, diverse and difficult problems, and reduces human effort. • Problem generation is formulated as a Markov Decision Process. • Generative policies are trained with Deep Reinforcement Learning. • Problem constraints are encoded via a novel semi-declarative. language In the field of Automated Planning there is often the need for a set of planning problems from a particular domain, e.g., to be used as training data for Machine Learning methods or as benchmarks in planning competitions. In most cases, these problems are created either by hand or by a domain-specific generator, putting a burden on the human designers. In this paper, we propose NeSIG ( Neuro-Symbolic Instance Generator ), to the best of our knowledge the first domain-independent method for automatically generating typed-STRIPS planning problems that are valid, diverse and difficult to solve. We formulate problem generation as a Markov Decision Process and train two generative policies with Deep Reinforcement Learning to generate problems with the desired properties. We conduct experiments on five classical domains, comparing our approach against handcrafted, domain-specific instance generators and various ablations. Results show NeSIG is able to automatically generate valid and diverse problems of much greater difficulty (6.8 times more on geometric average) than domain-specific generators, while simultaneously reducing human effort when compared to them. Additionally, it can generalize to problems more than twice the size of those seen during training.

Authors 3

1. Carlos Núñez-Molina corresponding Aachen Chair of Machine Learning and Reasoning

   RWTH Aachen University

   Affiliation as printed

   Chair of Machine Learning and Reasoning, RWTH Aachen University, Aachen, Germany

2. Pablo Mesejo

   Universidad de Granada

   Affiliation as printed

   Andalusian Institute of Data Science and Computational Intelligence (DaSCI), Granada, Spain

   Department of Computer Science and AI, University of Granada, Granada, Spain

3. Juan Fernández-Olivares

   Universidad de Granada

   Affiliation as printed

   Andalusian Institute of Data Science and Computational Intelligence (DaSCI), Granada, Spain

   Department of Computer Science and AI, University of Granada, Granada, Spain