UTS site search

Jesse Clark


Jesse Clark is a software engineer who has built distributed systems for a number of Silicon Valley startups. At NASA he developed databases for the International Space Station and robotic simulations for the Hubble Space Telescope.
Senior Research Engineer, School of Software
Core Member, Centre for Artificial Intelligence
Computer Science, Mathematical Sciences


Raza, S.A., Clark, J. & Williams, M. 2016, 'On Designing Socially Acceptable Reward Shaping', Social Robotics, International Conference on Social Robotics, Springer, Kansas City, MO, USA, pp. 860-869.
View/Download from: UTS OPUS or Publisher's site
For social robots, learning from an ordinary user should be socially appealing. Unfortunately, machine learning demands an enormous amount of human data, and a prolonged interactive teaching session becomes anti-social. We have addressed this problem in the context of reward shaping for reinforcement learning. For efficient reward shaping, a continuous stream of rewards is expected from the teacher. We present a simple framework which seeks rewards for a small number of steps from each of a large number of human teachers. Therefore, it simplifies the job of an individual teacher. The framework was tested with online crowd workers on a transport puzzle. We thoroughly analyzed the quality of the learned policies and crowd's teaching behavior. Our results showed that nearly perfect policies can be learned using this framework. The framework was generally acceptable in the crowd's opinion.