We study whether next-token prediction can yield world models that truly support planning, in a controlled symbolic setting where propositional STRIPS action models are learned from action traces alone and correctness can be evaluated exactly. We introduce two architectures. The first is the STRIPS Transformer, a symbolically aligned model grounded in theoretical results linking transformers and the formal language structure of STRIPS domains. The second is a standard transformer architecture without explicit symbolic structure built in, for which we study different positional encoding schemes and attention aggregation mechanisms. We evaluate both architectures on five classical planning domains, measuring training accuracy, generalization, and planning performance across domains and problem sizes. Interestingly, both approaches can be used to produce models that support planning with off-the-shelf STRIPS planners over exponentially many unseen initial states and goals. Although the STRIPS Transformer incorporates a strong symbolic inductive bias, it is harder to optimize and requires larger datasets to generalize reliably. In contrast, a standard transformer with stick-breaking attention achieves near-perfect training accuracy and strong generalization. Finally, standard transformers without stick-breaking attention do not generalize to long traces, whereas a symbolic STRIPS model extracted from a transformer trained on shorter traces does.

• 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.

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.

In the history of AI, two main paradigms have been proposed to solve Sequential Decision Making (SDM) problems: Automated Planning (AP) and Reinforcement Learning (RL). Among the many proposals to unify both fields, the one known as neurosymbolic AI has recently attracted great attention. It combines the Deep Neural Networks used in modern RL with the symbolic representations typical of AP. The main goal of this PhD is to progress the state of the art in neurosymbolic AI for SDM, developing methods for both solving these problems and learning aspects of their structure.