I am a PhD candidate in Computer Science at McGill University and Mila co-supervised by
Prof. David Meger
and Prof. Doina Precup.
I'm interested in temporal and state abstraction in reinforcement learning, particularly in the context of robotics for learning skills
across a wide range of tasks. During my MSc, I worked on data-efficient methods for learning robot dynamics for
control and interaction inference.
Samsung AI Centre, Montreal, Canada
Multimodal generative models for visuotactile perception.
Deep reinforcement learning for 5G networks.
Ubisoft La Forge, Montreal, Canada
Deep reinforcement learning for automated video game testing.
Samsung AI Centre, Montreal, Canada
Object detection neural networks for human hand-wave motions.
Implemented the vision stack on-board of a mobile robot.
McGill University, Montreal, Canada
Sep. 2020 - Present
PhD in Computer Science
Supervisors: David Meger, Doina Precup
University of Tehran, Tehran, Iran
Sep. 2012 - Sep. 2016
Bachelor of Engineering in Mechanical Engineering
Conferences and Journals
Learning Intuitive Physics with Multimodal Generative Models
Sahand Rezaei-Shoshtari, Francois R. Hogan, Michael Jenkin, David Meger, and Gregory Dudek. In
Thirty-Fifth AAAI Conference on Artificial Intelligence. 2021.
Seeing Through your Skin: Recognizing Objects with a Novel Visuotactile Sensor
Francois R. Hogan, Michael Jenkin,
Sahand Rezaei-Shoshtari, Yogesh Girdhar, David Meger, and Gregory Dudek. In
The IEEE Winter Conference on Applications of Computer Vision (WACV). 2021.
Learning the Latent Space of Robot Dynamics for Cutting Interaction Inference
Sahand Rezaei-Shoshtari, David Meger, and Inna Sharf. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2020.
Cascaded Gaussian Processes for Data-efficient Robot Dynamics Learning
Sahand Rezaei-Shoshtari, David Meger, and Inna Sharf. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2019.
Jacobian of Conditional Generative Models for Sensitivity Analysis of Photovoltaic Device Processes
Sahand Rezaei-Shoshtari, Nathaniel Quitoriano.
In Machine Learning for Engineering Workshop @ NeurIPS 2020.
Seeing Through Your Skin: A Novel Visuo-Tactile Sensor for Robotic Manipulation
Francois R. Hogan,
Sahand Rezaei-Shoshtari, Michael Jenkin, Yogesh Girdhar, David Meger, and Gregory Dudek. In
Workshop on Visual Learning and Reasoning for Robotic Manipulation @ RSS 2020.
Gym Forest Fire
Simulation of a Forest Fire Environment for Reinforcement Learning:
Fully vectorized forest fire simulation based cellular automaton.
With OpenAI Gym interface and an implementation of TD3 with CNN actor and critic.
Motion Planning and Control Utilities for Kinova Jaco 2 Arm
ROS package for Kinova Jaco 2 implementing:
Impedance control, feedforward torque control, and velocity control utilities.
Motion planning utilities for joint space and Cartesian space planning.
Implementations of Deep RL algorithm:
Minimalistic Deep RL implementations as an educational resource.
Fork of OpenAI Spinning Up with additional algorithms.
Learning Quadrotor Controls Using Data-Efficient Model-based Reinforcement Learning
Implementation of PILCO on a quadrotor for:
Learning the quadrotor dynamics.
Learning the quadrotor control policies under the loss of an actuator.
ANITI Reinforcement Learning Virtual School (RLVS) 2021 Hosted by ANITI. Virtual. March 2021.
Simons Institute Mathematics of Online Decision Making Workshop Hosted by Simons Institute. Virtual. October 2020.
CIFAR Deep Learning and Reinforcement Learning Summer School Hosted by CIFAR and Amii in Edmonton, Canada. July 2019.
Copyright © 2021 Sahand Rezaei-Shoshtari