Amir-massoud Farahmand


Mitsubishi Electric Research Laboratories (MERL)

Professional Background

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

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, please 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. BulletSince 2014 December, I joined the Data Analytics group of Mitsubishi Electric Research Laboratories (MERL).

  2. BulletApproximate MaxEnt Inverse Optimal Control and its Application for Mental Simulation of Human Interactions is accepted at AAAI Conference on Artificial Intelligence (AAAI), 2015. Joint work with De-An, Kris, and Drew. Extended version with proofs is here.

  3. BulletClassification-based Approximate Policy Iteration is accepted and will appear in IEEE Transactions on Automatic Control most likely by the end of 2015 (preprint; IEEE version). An extended version, which includes experiments and more discussions, is also available. Joint work with Doina, André, and Mohammad.

  4. BulletWe organized Sequential Decision-Making with Big Data workshop at AAAI-2014.  It had a great lineup of speakers and a room full of audience. Thank you all! Hope you enjoyed it.

  5. BulletSample-based Approximate Regularization is accepted and presented at the International Conference on Machine Learning (ICML), 2014. Joint work with Philip Bachman and Doina. Extended version with proofs is here.

  6. BulletI left McGill University after more than two years of working on many interesting projects with Doina Precup, Joelle Pineau and other wonderful members of the Reasoning and Learning Lab. The good news is that I am joining the Robotics Institute, Carnegie Mellon University to work with Drew Bagnell.

  7. BulletTwo papers at the Neural Information Processing Systems (NIPS) conference, 2013. Learning from Limited Demonstrations and Bellman Error Based Feature Generation using Random Projections on Sparse Spaces. Joint work with Beomjoon, Doina, Joelle, Mahdi, and Yuri.

  8. BulletPhD Outstanding Thesis Award for the period of 2011-2012, Department of Computing Science, University of Alberta, 2013.

Academic blog: ThesiLog

Persian blog: ضدخاطرات

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 Optimal Control: high-dimensional problems, regularized algorithms, inverse optimal control

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

  4. BulletOther Industrial Applications: hybrid vehicle energy management

  5. BulletLarge-scale Optimization

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