Seminar: Reinforcement Learning

Amir-Massoud Farahmand, Mitsubishi Electric Research Laboratories (MERL)

Speaker: Amir-Massoud Farahmand, Mitsubishi Electric Research Laboratories (MERL)

Reinforcement learning (RL) is the problem of designing an agent that interacts with its environment and gradually improves its performance. The agent can be a computer system that plays Atari games or the game of Go, as has recently been developed by Google DeepMind. The RL agent can also be an energy management system in a hybrid car whose goal is to maximize the car’s energy efficiency, or an ever-improving smart home’s air-conditioning system whose goal is to maximize the occupants’ comfort while minimizing the operation costs. In this presentation, I will talk about some of the advances that we have had at Mitsubishi Electric Research Labs (MERL) in designing new RL algorithms and applying them to these industrial applications.

  • Monday, October 24, 2016 @ 2:30 pm
  • Arts 263
  • Everyone is welcome to attend!


Amir-massoud Farahmand is a principal research scientist at Mitsubishi Electric Research Laboratories (MERL) in Cambridge, USA. His research interests are in reinforcement learning and machine learning with a focus on developing theoretically-sound algorithms for challenging industrial problems. 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).

Amir-massoud is the recipient of Natural Sciences and Engineering Research Council of Canada (NSERC) postdoctoral fellowship. His work received the University of Alberta’s Department of Computing Science Ph.D. Outstanding Thesis Award for the period of 2011–2012, and has been published in top machine learning (JMLR, MLJ, NIPS, ICML, AAAI), control engineering (IEEE TAC, CDC, ACC), and robotics (IROS and ICRA) venues.