Socially GuidedMachine Learning

Social interaction will be key to enabling robots and machines in general to learn new tasks from ordinary people (not experts in robotics ormachine learning). Everyday people who need to teach their machines new things will find it natural for to rely on their interpersonal interaction skills. This thesis provides several contributions towards the understanding of this Socially GuidedMachine Learning scenario. While the topic of human input tomachine learning algorithms has been explored to some extent, prior works have not gone far enough to understandwhat people will try to communicate when teaching a machine and how algorithms and learning systems can be modified to better accommodate a human partner. Interface techniques have been based on intuition and assumptions rather than grounded in humanbehavior, and often techniques are not demonstrated or evaluated with everyday people. Using a computer game, Sophie’s Kitchen, an experiment with human subjects provides several insights about howpeople approach the task of teaching amachine. In particular, people want to direct and guide an agent’s exploration process, they quickly use the behavior of the agent to infer amentalmodel of the learning process, and they utilize positive and negative feedback in asymmetric ways. Using a robotic platform, Leonardo, and 200 people in follow-up studies of modified versions of the Sophie’s Kitchen game, four research themes are developed. The use of human guidance in amachine learning exploration canbe successfully incorporated to improve learning performance. Novel learning approaches demonstrate aspects of goal-oriented learning. The transparency of themachine learner can have significant effects on the nature of the instruction received from the human teacher, which in turn positively impacts the learning process. Utilizing asymmetric interpretations of positive and negative feedback from a human partner, can result in a more efficient and robust learning experience. Thesis Supervisor: Cynthia Breazeal Title: Associate Professor of Media Arts & Sciences