- Reinforcement Learning
- Statistical Learning Theory
Amir-massoud Farahmand is a faculty member, research scientist, and CIFAR AI Chair at the Vector Institute in Toronto, Canada. He is also an assistant professor at the Department of Computer Science, University of Toronto.
He received his PhD from the University of Alberta in 2011, followed by postdoctoral fellowships at McGill University (2011–2014) and Carnegie Mellon University (CMU) (2014). Prior to joining the Vector Institute, he was a principal research scientist at Mitsubishi Electric Research Laboratories (MERL) in Cambridge, USA for three years, working on developing theoretically-sound algorithms for challenging industrial problems.
Amir-massoud’s research goal is designing an agent that controls its stream of experience, by learning how the outside and inside worlds work while focusing on aspects that are most relevant to its decision making. He takes a theoretical approach to this goal.
- Best reviewer or outstanding area chair awards for International Conference on Machine Learning (ICML) (2015, 2019), Neural Information Processing Systems (NeurIPS) (2019), International Conference on Learning Representations (ICLR) (2018, 2021).
- NSERC Postdoctoral Fellowship, 2012–2014
- PhD Outstanding Thesis Award, Department of Computing Science, University of Alberta, 2012.
Research Activity and News
- Developed a new course on Reinforcement Learning. All videos can be accessed through this playlist. The course is accompanied by the in-progress short textbook Lecture Notes in Reinforcement Learning.
- A.M. Farahmand and Mohammad Ghavamzadeh, “PID Accelerated Value Iteration Algorithm,” International Conference on Machine Learning (ICML), 2021.
- A.M. Farahmand, “Value Function in Frequency Domain and the Characteristic Value Iteration Algorithm,” In the Proceedings of Advances in Neural Information Processing Systems (NeurIPS), 2019.
- A.M. Farahmand, “Iterative Value-Aware Model Learning,” Neural Information Processing Systems (NeurIPS), 2018.