Harsh Satija

I am a PhD student supervised by Prof. Joelle Pineau at McGill University and Mila. I am primarily interested in Reinforcement Learning and Artificial Intelligence Safety, with a focus on building efficient algorithms that prevent harm.

Research Summary: With an increasing number of automated decision-making algorithms being deployed around us, it becomes important to address the safety risks and biases associated with these algorithms, as machine learning algorithms in general, have shown to have the ability to inflict unintended behavior or harm if not developed or deployed with care in a societal setting. My research takes steps towards this goal by building efficient Reinforcement Learning algorithms in settings where the primary focus is on the problem of learning intelligent behaviour for accomplishing a task, but with additional requirements on the nature of the algorithm’s behaviour that can be related to safety, reliability or fairness.

I am on the job market for industry positions. Please reach out if I'd be a good fit for your research group.

Email  |  Google Scholar  |  LinkedIn  |  CV

profile photo



News
Research
sym

Group Fairness in Reinforcement Learning
Harsh Satija, Matteo Pirotta, Alessandro Lazaric, Joelle Pineau.
In Transactions on Machine Learning Research (TMLR), 2023.
An earlier version appeared in European Workshop on Reinforcement Learning (EWRL), 2022, Oral

pdf | abstract | bibtex | code

sym

Multi-Objective SPIBB
Harsh Satija, Philip S. Thomas, Joelle Pineau, Romain Laroche.
Neural Information Processing Systems (NeurIPS), 2021.

pdf | abstract | bibtex | code

sym

Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards.
Susan Amin, Maziar Gomrokchi, Hossein Aboutalebi, Harsh Satija, Doina Precup .
International Conference on Machine Learning (ICML), 2021.

pdf | abstract | bibtex | code

sym

Constrained Markov Decision Processes via Backward Value Functions.
Harsh Satija, Philip Amortila, Joelle Pineau.
International Conference on Machine Learning (ICML), 2020.

pdf | abstract | bibtex | code

sym

A Survey of Exploration Methods in Reinforcement Learning.

Susan Amin, Harsh Satija*, Maziar Gomrokchi*, Herke Van Hoof*, Doina Precup.
In review

pdf | abstract | bibtex

sym

Randomized value functions via multiplicative normalizing flows.
Ahmed Touati, Harsh Satija, Joshua Romoff, Joelle Pineau, Pascal Vincent.
Uncertainty in Artificial Intelligence (UAI), 2020

pdf | abstract | bibtex | code

sym

Decoupling dynamics and reward for transfer learning.
Harsh Satija*, Amy Zhang*, Joelle Pineau.
International Conference on Learning Representations (ICLR) Workshop Track, 2018.

pdf | abstract | bibtex | code


Modified version of the template from this, this and this .