Hello, I’m Samuel Neumann, a PhD student at the University of Alberta.
You can find my CV here.
Education and Research Interests
I completed my Bachelor of Science at MacEwan University, majoring in both Mathematics and Computing Science. During my undergraduate career, I held two NSERC USRA awards which funded research in machine learning. Upon graduation, I received the Governor General’s Silver Medal for highest GPA in my graduating class.
After receiving my Bachelor of Science, I went on to complete a Master of Science at the University of Alberta. I was supervised by Adam White, and my research was in Reinforcement Learning. Particularly, I studied actor-critic algorithms and their relation to approximate policy iteration. During my Master of Science program, I attained an NSERC CGS-M award as well as the Alberta Graduate Excellence Scholarship and the Alberta Innovates Graduate Student Scholarship. I am extremely grateful to these organizations for their financial support during my Master of Science program.
Now, I am a PhD student at the University of Alberta, supervised by Adam White. My current research still revolves around actor-critic algorithms. In particular, I’ve been continuing my study of these algorithms from an approximate policy iteration perspective. Although I’m interested in everything actor-critic, my recent research has focused on how actor-critic algorithms are affected by:
- New policy improvement operators
- Entropy regularization
- Policy parameterizations
with a particular focus on variants of the Soft Actor-Critic algorithm and the Greedy Actor-Critic algorithm.
Random Stuff
- I’m the moderator for the Reinforcement Learning Coursera MOOC, which is put out by the University of Alberta and Amii.