Amir-massoud Farahmand


Machine Learning Researcher
Mitsubishi Electric Research Laboratories (MERL)


PhD in Computer Science, University of Alberta (CS)
(Working with Csaba Szepesvári and Martin Jägersand), 2011

NSERC Postdoctoral Fellow, McGill University (SCS)
(Working with Doina Precup), 2011-2014

NSERC Postdoctoral Fellow, Carnegie Mellon University (RI)
(Working with J. Andrew Bagnell), 2014

Research Goal

Very Short – Two perspectives:

  1. BulletUse data not only to predict, but also to control [ML Perspective].

  2. BulletDesigning adaptive situated agent [AI Perspective].


In the 21st century, we live in a world where data is abundant. We would like to take advantage of this opportunity to make more accurate and data-driven decisions in many areas of life such as industry, healthcare, business, and government. Even though many machine learning and data mining researchers have developed tools to benefit from “big data”, their methods so far have mostly been about the task of prediction.

My goal, however, is to use data to control, that is, taking actions in an uncertain world with a complex dynamics in order to achieve a long-term goal such as maximizing the relief of a patient with a chronic disease, sustainable management of natural resources, or increasing the comfort of a building’s occupants.

Admittedly, we are not there yet. Theoretical foundations should be laid and technologies must be developed. But I believe that data-driven decision making defines a new era in human civilization, and my research moves us toward that era. For more details about data-driven control and decision making and understanding my contributions, refer to my Research Statement or take a look at my Publications. Also if you have any questions, please feel free to contact me.


    1. BulletTwo papers on Random Projection Filter Bank (RPFB) are accepted: One at NIPS 2017 and another at PHM 2017 (I will post links later). Joint work with Sepideh Pourazarm and Daniel Nikovski. Summary: To extract features from a time series, project it onto the span of randomly generated stable dynamical filters. Similar to Random Kitchen Sink, but for dynamical systems.

    2. BulletValue-Aware Model Function for Model-based Reinforcement Learning is published at AISTATS 2017. Joint work with Andre and Daniel. Summary: A good model for prediction is not necessarily a good model for model-based RL as it ignores the decision problem. How can we incorporate the decision problem?

    3. BulletTwo papers on controlling Partial Differential Equations (PDE) using reinforcement learning: 1) Learning to Control Partial Differential Equations: Regularized Fitted Q-Iteration (CDC 2016), and 2) Deep Reinforcement Learning for Partial Differential Equation Control (ACC 2017). Joint work with Saleh Nabi, Daniel Nikovski, and Piyush Grover.

    BulletRegularized Policy Iteration with Nonparametric Function Spaces is published at the Journal of Machine Learning Research (JMLR), 2016. Joint work with Csaba, Mohammad, and Shie. Summary: Regularized Least Squares Temporal Difference (LSTD) is introduced and analyzed. The method is minimax optimal in a large class of nonparametric function spaces.

Persian blog: ضدخاطرات

Academic blog: ThesiLog (inactive!)

Academic and Non-academic Tweets

Research Interests

  1. BulletMachine Learning and Statistics: statistical learning theory, nonparametric algorithms, regularization, manifold learning, non-i.i.d. processes, online learning

  2. BulletReinforcement Learning, Sequential Decision Making, and Control: high-dimensional problems, regularized nonparametric algorithms, inverse optimal control

  3. BulletRobotics: uncalibrated visual servoing, learning from demonstration, behaviour-based architecture for robot control

  4. BulletIndustrial Applications: hybrid vehicle energy management

  5. BulletEvolutionary Computation: cooperative co-evolution, interaction of evolution and learning

  6. BulletLarge-scale Optimization