Portrait of Amir-massoud Farahmand

Amir-massoud Farahmand

Core Academic Member
farahmand@mila.quebec
Associate Professor, Polytechnique Montréal
University of Toronto
Research Topics
Deep Learning
Machine Learning Theory
Reasoning
Reinforcement Learning
Website
Google Scholar
LinkedIn
X

Biography

Amir-massoud Farahmand is an associate professor at the Department of Computer and Software Engineering, Polytechnique Montréal and a core academic member at Mila - Quebec Artificial Intelligence Institute, as well as an associate professor (status-only) at the Department of Computer Science, University of Toronto. He was a research scientist and CIFAR AI Chair at the Vector Institute in Toronto between 2018–2024, and principal research scientist at Mitsubishi Electric Research Laboratories (MERL) in Cambridge, USA between 2014-2018. 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’s research vision is to understand the computational and statistical mechanisms required to design efficient AI agents that interact with their environment and adaptively improve their long-term performance. He has experience in developing Reinforcement Learning and Machine Learning methods to solve industrially-motivated problems as well.

Current Students

Nimrod De La Vega
PhD
nimrod.delavega@gmail.com
Website
Navid Ghassemi
Collaborating researcher - McGill University University
Tyler Kastner
Collaborating researcher - University of Toronto
tyler.kastner@mail.mcgill.ca

Publications

Dissecting Deep RL with High Update Ratios: Combatting Value Overestimation and Divergence
Marcel Hussing
Claas Voelcker
Igor Gilitschenski
Amir-massoud Farahmand
Eric R. Eaton
We show that deep reinforcement learning can maintain its ability to learn without resetting network parameters in settings where the number… (see more) of gradient updates greatly exceeds the number of environment samples. Under such large update-to-data ratios, a recent study by Nikishin et al. (2022) suggested the emergence of a primacy bias , in which agents overfit early interactions and downplay later experience, impairing their ability to learn. In this work, we dissect the phenomena underlying the primacy bias. We inspect the early stages of training that ought to cause the failure to learn and find that a fundamental challenge is a long-standing acquaintance: value overestimation. Overinflated Q-values are found not only on out-of-distribution but also in-distribution data and can be traced to unseen action prediction propelled by optimizer momentum. We employ a simple unit-ball normalization that enables learning under large update ratios, show its efficacy on the widely used dm_control suite, and obtain strong performance on the challenging dog tasks, competitive with model-based approaches. Our results question, in parts, the prior explanation for sub-optimal learning due to overfitting on early data.
2024-03-01
arXiv (published)
doi.org
Dissecting Deep RL with High Update Ratios: Combatting Value Divergence.
Marcel Hussing
Claas Voelcker
Igor Gilitschenski
Amir-massoud Farahmand
Eric R. Eaton
2024-01-01
RLJ (published)
arxiv.org
arxiv.org
PID Accelerated Temporal Difference Algorithms
Mark Bedaywi
Amin Rakhsha
Amir-massoud Farahmand
Long-horizon tasks, which have a large discount factor, pose a challenge for most conventional reinforcement learning (RL) algorithms. Algor… (see more)ithms such as Value Iteration and Temporal Difference (TD) learning have a slow convergence rate and become inefficient in these tasks. When the transition distributions are given, PID VI was recently introduced to accelerate the convergence of Value Iteration using ideas from control theory. Inspired by this, we introduce PID TD Learning and PID Q-Learning algorithms for the RL setting, in which only samples from the environment are available. We give a theoretical analysis of the convergence of PID TD Learning and its acceleration compared to the conventional TD Learning. We also introduce a method for adapting PID gains in the presence of noise and empirically verify its effectiveness.
2024-01-01
RLJ (published)
doi.org
arxiv.org