Publication List

Thesis

Towards alignment of Reinforcement Learning agents; for consideration of safety, robustness and fairness.

Harsh Satija

PhD Thesis, McGill University 2023
Paper

Conference

Multi-Objective SPIBB

Harsh Satija, Philip S. Thomas, Joelle Pineau, Romain Laroche

NeurIPS 2021
Paper

Github
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards

Susan Amin, Maziar Gomrokchi, Hossein Aboutalebi, Harsh Satija, Doina Precup

ICML 2021
Paper

Github
Randomized value functions via multiplicative normalizing flows

Ahmed Touati, Harsh Satija, Joshua Romoff, Joelle Pineau, Pascal Vincent

UAI 2020
Paper

Github
Constrained Markov Decision Processes via Backward Value Functions.

Harsh Satija, Philip Amortila, Joelle Pineau

ICML 2020
Paper

Github

Journal

Group Fairness in Reinforcement Learning

Harsh Satija, Matteo Pirotta, Alessandro Lazaric, Joelle Pineau

TMLR 2023
Oral at EWRL 2022

Paper

Github

Workshop

Decoupling dynamics and reward for transfer learning

Harsh Satija*, Amy Zhang*, Joelle Pineau

ICLR 2019
Paper

Github

Preprint

A Survey of Exploration Methods in Reinforcement Learning

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

JAIR (In review)
Paper