The Effect of Multi-step Methods on Overestimation in Deep Reinforcement Learning

I am a CSIRO Early Research Career (CERC) Postdoctoral Fellow at CSIRO Technology and an Adjunct Lecturer in Electrical and Computer Systems Engineering at Monash University. My research asks how to make robots that learn from and act alongside people robust and trustworthy in real-world deployment. I work on deep reinforcement learning, preference learning, and human-robot interaction, applied to manipulation, legged locomotion, and assistive robotics. I received my PhD from the University of Waterloo in 2023.