Planning with Neural (and Large) Language Models

Abstract

In recent years, deep learning and neural language models have achieved promising results not only in traditional application areas, such as natural language processing and computer vision, but also in the more formal and rigorous field of automated planning. This seminar will present some of these applications, focusing in particular on the development of recurrent neural networks for goal recognition, the adaptation of Transformer-based models to automated planning, and the use of these models to solve planning problems. It will discuss the techniques and strategies employed, as well as the main limitations, potential future directions, and open research questions.

About the Speaker

Dr. Luca Putelli is an Assistant Professor at the University of Brescia (Italy) where he received his Ph.D. in Information Engineering in 2021. His main research interests are Natural Language Processing and Explainable AI, with a particular focus on real-world applications, semantics, word representation and fairness in Transformer-based models. He also works in neuro-symbolic AI, where he has contributed to the creation of several deep learning models applied to automated planning, in particular for goal recognition and plan generation with Large Language Models