I am a Research Scientist at Google Brain, where I mainly work on problems in deep learning, reinforcement learning, robotics, and probabilistic machine learning. My recent research focuses on sample-efficient RL methods that could scale to solve difficult continuous control problems in the real-world, which have been covered by Google Research Blogpost and MIT Technology Review.

I completed PhD in Machine Learning at the University of Cambridge and the Max Planck Institute for Intelligent Systems in Tübingen, where I was co-supervised by Richard E. TurnerZoubin Ghahramani, and Bernhard Schölkopf. During my PhD, I also collaborated closely with Sergey Levine at UC Berkeley/Google Brain and Timothy Lillicrap at DeepMind. I hold my B.ASc. in Engineering Science from the University of Toronto, where I did my thesis with Geoffrey Hinton in distributed training of neural networks using evolutionary algorithms. I also had great fun time working with Steve Mann, developing real-time HDR capture for wearable cameras/displays.  I interned at Google Brain hosted by Ilya Sutskever and Vincent Vanhoucke. I also volunteered as a Lab Scientist at Creative Destruction Lab, one of the leading tech-startup incubators in Canada. My PhD was funded by Cambridge-Tübingen PhD FellowshipNSERC and Google Focused Research Award.

I am a Japan-born Chinese Canadian, and I speak, read, and write in three languages. Having lived in Japan, China, Canada, the US, the UK, and Germany, I go under multiple names: Shane Gu, Shixiang Gu, 顾世翔, 顧世翔(ぐう せいしょう).