Follow
Harsh Satija
Harsh Satija
McGill University, Mila
Verified email at mail.mcgill.ca
Title
Cited by
Cited by
Year
A survey of exploration methods in reinforcement learning
S Amin, M Gomrokchi, H Satija, H Van Hoof, D Precup
arXiv preprint arXiv:2109.00157, 2021
972021
Decoupling dynamics and reward for transfer learning
A Zhang, H Satija, J Pineau
arXiv preprint arXiv:1804.10689, 2018
922018
Constrained markov decision processes via backward value functions
H Satija, P Amortila, J Pineau
International Conference on Machine Learning (ICML) 2020, 2020
672020
Simultaneous machine translation using deep reinforcement learning
H Satija, J Pineau
ICML 2016 Workshop on Abstraction in Reinforcement Learning, 2016
472016
Randomized value functions via multiplicative normalizing flows
A Touati, H Satija, J Romoff, J Pineau, P Vincent
Uncertainty in Artificial Intelligence, 422-432, 2020
422020
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards
S Amin, M Gomrokchi, H Aboutalebi, H Satija, D Precup
International Conference on Machine Learning (ICML) 2021, 2020
252020
Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs
H Satija, PS Thomas, J Pineau, R Laroche
Advances in Neural Information Processing Systems (NeurIPS) 2021, 2021
20*2021
Disaggregating latent causes for computer system optimization
MO Hashemi, P Ranganathan, H Satija
US Patent 10,650,001, 2020
42020
Group Fairness in Reinforcement Learning
H Satija, A Lazaric, M Pirotta, J Pineau
Transactions on Machine Learning Research, 2023
22023
Towards alignment of Reinforcement Learning agents; for consideration of safety, robustness and fairness.
H Satija
McGill University, 2024
2024
Disaggregating latent causes for computer system optimization
MO Hashemi, P Ranganathan, H Satija
US Patent 11,275,744, 2022
2022
The system can't perform the operation now. Try again later.
Articles 1–11