Hello, my name is Norman.


I am a masters student at the University of Western Ontario in Canada. My research focuses on reinforcement learning. The primary objectives of my work is to improve agent performance, data efficiency, and task transferability in complex environments. My research is applicable to financial markets (algorithmic trading), control systems, and robotics.

In my spare time I enjoy creating and maintaining profitable trading algorithms. Currently, I am applying reinforceforment learning and statistical models to cryptocurrency markets.


Dynamic Planning Networks: Learning to dynamically create state-actions trees to improve planning performance https://arxiv.org/abs/1812.11240.

I worked fulltime at Scaled Inference in Palo Alto, CA. My work focused on distributed systems and a bit of machine learning.

I am the author of PLE a reinforcement learning environment for python.

Interned at Scaled Inference in Palo Alto, CA. My internship focused on the combination of bayesian models and deep neural networks. Additionally, I spent time improving modeling speed by porting code to run on GPUs.

Interned at Flipboard working on Image Super Resolution and bayesian optimization of hyperparameters over clusters.

Performed research at the University of Western Ontario focusing on anomaly detection with electrical stream data using machine learning methods.


@normantasfi or email (n plus tasfi at google email)