Con gran convocatoria, el Departamento de Ingeniería Informática realizó la charla dictada por el Dr. Francisco Cruz Naranjo (Profesor asistente UNSW Sydney Australia) titula “Explainable Robotic Systems in Reinforcement Learning Scenarios”. El evento se realizaró el día martes 21 de marzo a las 15:20 hrs en la sala 201 del Departamento de Ingeniería Informática DIINF-USACH.
Abstract: Robotic systems are more present in our society everyday. In human-robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To increase action understanding, users demand more explainability about the decisions by the robot in particular situations. Recently, explainable robotic systems have emerged as an alternative focused not only on completing a task satisfactorily but also on justifying, in a human-like manner, the reasons that lead to making a decision. In reinforcement learning scenarios, a great effort has been focused on providing explanations using data-driven approaches, particularly from the visual input modality in deep learning-based systems. This talk focuses rather on the decision-making process of reinforcement learning agents performing a task in robotic scenarios.
Revisa la presentación en el siguiente link: Presentación “Explainable Robotic Systems in Reinforcement Learning Scenarios”