Bei Peng
Office: Dana Hall 2
Email: bei.peng@wsu.edu Phone: 509-330-6580
I am a PhD student at the IRL lab of Washington State University, working with Prof. Matthew E. Taylor.

My research mainly focuses on interactive machine learning, reinforcement learning, and curriculum learning. The main goal of interactive machine learning is to combine AI systems with human intelligence, such that the systems can learn more efficiently from humans when needed, and non-expert humans can access the benefits of machine learning. This is important since the deployment of real-world robotic systems requires to be adaptive to many different complex human environments. A reliable AI system needs to work with humans, not alone. We need to better understand how human teachers want to teach the agent so that we can better model them to gain more effective learning interaction. So I have been working on exploring how to better interpret, incorporate, and allocate human feedback to speed up agent learning. I also work on designing a better representation of the learning agent to elicit a more natural and effective learning interaction between the human and the learner. Currently, I focus on curriculum learning in the context of reinforcement learning.