h i g h l i g h t s • Reinforcement learning's option switches are analogous to psychological insight. • Insight and options reveal comparable capabilities for transformational creativity. • Open problems remain: lifelong learning, switching when exploring, option discovery.
Enabling users to teach their robots new tasks at home is a major challenge for research in personal robotics. This work presents a user study in which participants were asked to teach the robot Pepper a game of skill. The robot was equipped with a state-of-the-art skill learning method, based on dynamic movement primitives (DMPs). The only feedback participants could give was a discrete rating after each of Pepper's movement executions ("very good," "good," "average," "not so good," "not good at all"). We compare the learning performance of the robot when applying user-provided feedback with a version of the learning where an objectively determined cost via hand-coded cost function and external tracking system is applied. Our findings suggest that (a) an intuitive graphical user interface for providing discrete feedback can be used for robot learning of complex movement skills when using DMP-based optimization, making the tedious definition of a cost function obsolete; and (b) un-experienced users with no knowledge about the learning algorithm naturally tend to apply a working rating strategy, leading to similar learning performance as when using the objectively determined cost. We discuss insights about difficulties when learning from user provided feedback, and make suggestions how learning continuous movement skills from non-expert humans could be improved.
Artificial object perception usually relies on a priori defined models and
feature extraction algorithms. We study how the concept of object can be
grounded in the sensorimotor experience of a naive agent. Without any knowledge
about itself or the world it is immersed in, the agent explores its
sensorimotor space and identifies objects as consistent networks of
sensorimotor transitions, independent from their context. A fundamental drive
for prediction is assumed to explain the emergence of such networks from a
developmental standpoint. An algorithm is proposed and tested to illustrate the
approach.Comment: 7 pages, 4 figures, ICDL-Epirob 2015 conferenc
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.