Amir-massoud Farahmand is a Canada CIFAR AI Chair at the Vector Institute, an assistant professor in the department of computer science at the University of Toronto.
Farahmand’s research focuses on machine learning and reinforcement learning. He is interested in understanding the principles required to design reinforcement learning and adaptive situated agents. These agents interact with their environment, collect data, and use data not only to predict, but also to control the environment, with the goal of maximizing their long-term performance. He is particularly interested in solving difficult industrial problems using principles developed to design adaptive situated agents.
- Best Reviewer Award, International Conference on Learning Representations (ICLR), 2018
- Best Reviewer Award, International Conference on Machine Learning (ICML), 2015
- NSERC Postdoctoral Fellowship, 2012-2014
- PhD Outstanding Thesis Award, Department of Computing Science, University of Alberta, 2011-2012
- NSERC Pre-approved Industrial Research and Development Fellowship (IRDF) Candidate, 2012
- Farahmand, A. M. (2018). Iterative Value-Aware Model Learning. In NeurIPS (pp. 9090-9101).
- Farahmand, A. M., Barreto, A., & Nikovski, D. (2017). Value-aware loss function for model-based reinforcement learning. In Artificial Intelligence and Statistics (pp. 1486-1494). PMLR.
- Farahmand, A. M., Ghavamzadeh, M., Szepesvári, C., & Mannor, S. (2016). Regularized policy iteration with nonparametric function spaces. The Journal of Machine Learning Research, 17(1), 4809-4874.
- Farahmand, A. M., Munos, R., & Szepesvári, C. (2010). Error propagation for approximate policy and value iteration. In Advances in Neural Information Processing Systems.
- Farahmand, A. M., Ghavamzadeh, M., Szepesvári, C., & Mannor, S. (2008). Regularized policy iteration. In nips (pp. 441-448).
CIFAR is a registered charitable organization supported by the governments of Canada, Alberta and Quebec, as well as foundations, individuals, corporations and Canadian and international partner organizations.