Email: bei.peng@wsu.edu Phone:(509) 330-6580 Google scholar

News

7/3/2018: I defended my Ph.D. dissertation entitled Learning from Human Teachers: Supporting How People Want to Teach in Interactive Machine Learning.

5/30/2018: I got an internship offer from Microsoft research. I will be working with the reinforcement learning group in Redmond starting this September.

3/17/2018: Our journal paper has been accepted for publication in the IEEE Transactions on Emerging Topics in Computational Intelligence.

3/5/2018: I am now doing my internship at Borealis AI in Edmonton, Canada.

8/21/2017: I am now doing my internship at Tencent AI lab in Seattle.

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, without requiring them to have any experience with programming or artificial intelligent systems. 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 people want to teach the agent and better support the ways in which people want to teach the agent. So I have been working on studying how humans want to teach the agent using online evaluative feedback and how to learn more efficiently from limited feedback provided by human trainers. We have also worked on investigating how non-expert humans design a curriculum of tasks to help an agent learn some given target task and how to improve the learning algorithm using this non-expert guidance.