Jean Harb

I'm a fifth year Ph.D. student in Computer Science at McGill University, supervised by Doina Precup. I am a member of Mila.

My interests are in reinforcement learning and deep learning. I'm currently focussing on exploration and temporal abstraction within the deep RL setting.

During the summer of 2015, I interned at Maluuba as a research scientist. I worked on natural language processing using deep learning.

In the Spring of 2017, I interned at OpenAI, where I worked on multi-agent communication using Deep Reinforcement Learning.

During the Summer of 2018, and all of 2020, I interned at Deepmind - Montreal.

Here is my CV. I can be reached at jean.merheb-harb[at]mail.mcgill.ca

Jean Harb, Tom Schaul, Doina Precup, Pierre-Luc Bacon
Policy Evaluation Networks
arXiv preprint, 2020

Jean Harb*, Pierre-Luc Bacon*, Martin Klissarov, Doina Precup
When Waiting is not an Option: Learning Options with a Deliberation Cost
Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), 2018

Ryan Lowe*, Yi Wu*, Aviv Tamar, Jean Harb, Pieter Abbeel, Igor Mordatch
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
Neural Information Processing Systems (NIPS), 2017

Jean Harb, Pierre-Luc Bacon, Doina Precup
Asynchronous Advantage Option-Critic with Deliberation Cost
Conference on Reinforcement Learning and Decision Making (RLDM), 2017

Pierre-Luc Bacon, Jean Harb, Doina Precup
The Option-Critic Architecture
Thirty-First AAAI Conference on Artificial Intelligence (AAAI), 2017
Outstanding Student Paper Award

Jean Harb, Doina Precup
Investigating Recurrence and Eligibility Traces in Deep Q-Networks
NIPS 2016 Deep Reinforcement Learning Workshop