Felipe Meneguzzi

BIOgraphy

Felipe Meneguzzi is Chair of Computing Science at the University of Aberdeen and Bridges Professor at the Pontifical Catholic University of Rio Grande do Sul (PUCRS). He received his PhD degree in Computer Science from King's College London (KCL) and holds an MSc degree from PUCRS. His career includes a decade as a Professor at PUCRS in Brazil, a Research Fellowship at Carnegie Mellon University (CMU) in the US and a brief stint in industry at Hewlett Packard. Felipe's research focuses on reasoning mechanisms for autonomous agents integrating symbolic and connectionist approaches to achieve efficient, explainable and socially good behaviour by following societal norms. To this end, Felipe has contributed with approaches involving planning, machine learning and logic spanning the width of modern AI research. During his career in Brazil he was classified as a highly productive researcher (PQ-Fellow). Felipe received numerous awards for his work (including the 2016 and 2019 Google Research Award for Latin America), service, and through his students graduate work.

Title: Goal Recognition using Model Free Reinforcement Learning

Abstract

Goal Recognition aims to infer an agent's goal from a sequence of observations. While most existing approaches often rely on manually engineered domains and discrete representations, recent work has tried to obviate the need for such domains using machine learning. This talk covers recent methods we developed towards model free reinforcement learning applied to the problem of goal recognition. We start with tabular methods that show the viability of the such techniques and then show how we can employ deep reinforcement learning methods to overcome the usual problems of partial observability and noise. We proceed to discussing the interplay of such methods with agent architectures pointing to the future of research on machine learning and reasoning.