For over 7 years, I have been actively involved in conducting machine learning research. Recently, my focus has been on contributing to the development of fundamental reinforcement learning research in collaboration with students and scientists from DeepMind and UoA. Driven by my passion for creating exceptional products, I have started to apply my expertise in reinforcement learning to tackle real-world challenges. This began with optimizing the chemical levels in a water treatment plant and has since expanded to the realm of algorithmic trading.

Email: mhi.erfan1 at gmail dot com

(New) Investigating the Properties of Neural Network Representations in Reinforcement Learning
Han Wang, Erfan Miahi, Martha White, Marlos C Machado, Zaheer Abbas, Raksha Kumaraswamy, Vincent Liu, Adam White
Pre-print on arXiv
Paper

Genetic Neural Architecture Search for automatic assessment of human sperm images
Erfan Miahi, Seyed Abolghasem Mirroshandel, Alexis Nasr
Expert Systems and Applications
Paper

Effect of deep transfer and multi-task learning on sperm abnormality detection
Amir Abbasi^*, Erfan Miahi^*, Seyed Abolghasem Mirroshandel
Computers in Biology and Medicine
Paper/Code

Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances
Mojtaba Shakeri, Erfan Miahi, Abhishek Gupta, Yew-Soon Ong
IEEE Transactions on Cybernetics Journal
Paper/Code