NeSIG: A Neuro-Symbolic Method for Learning to Generate Planning Problems
This addresses the burden on human designers in automated planning by providing a domain-independent solution for generating planning problems, though it appears incremental as it builds on existing MDRL and neuro-symbolic approaches.
The paper tackles the problem of automatically generating planning problems for automated planning, which are typically created manually or with domain-specific generators, by proposing NeSIG, a domain-independent method that formulates problem generation as a Markov Decision Process and trains generative policies with Deep Reinforcement Learning. Results show NeSIG generates valid and diverse problems with 15.5 times greater difficulty on geometric average than domain-specific generators while reducing human effort.
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 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, to the best of our knowledge the first domain-independent method for automatically generating 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 three 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 (15.5 times more on geometric average) than domain-specific generators, while simultaneously reducing human effort when compared to them. Additionally, it can generalize to larger problems than those seen during training.