Joshua Romoff
Joshua Romoff
Ubisoft La Forge
Verified email at
Cited by
Cited by
Towards the systematic reporting of the energy and carbon footprints of machine learning
P Henderson, J Hu, J Romoff, E Brunskill, D Jurafsky, J Pineau
Journal of Machine Learning Research 21 (248), 1-43, 2020
Tarmac: Targeted multi-agent communication
A Das, T Gervet, J Romoff, D Batra, D Parikh, M Rabbat, J Pineau
International Conference on machine learning, 1538-1546, 2019
Hybrid reward architecture for reinforcement learning
H Van Seijen, M Fatemi, J Romoff, R Laroche, T Barnes, J Tsang
Advances in Neural Information Processing Systems 30, 2017
Reward estimation for variance reduction in deep reinforcement learning
J Romoff, P Henderson, A Piché, V Francois-Lavet, J Pineau
Conference on Robot Learning, 674-699, 2018
Where did my optimum go?: An empirical analysis of gradient descent optimization in policy gradient methods
P Henderson, J Romoff, J Pineau
arXiv preprint arXiv:1810.02525, 2018
Deep reinforcement learning for navigation in aaa video games
E Alonso, M Peter, D Goumard, J Romoff
Proceedings of the Thirtieth International Joint Conference on Artificial …, 2021
Randomized value functions via multiplicative normalizing flows
A Touati, H Satija, J Romoff, J Pineau, P Vincent
Uncertainty in Artificial Intelligence, 422-432, 2020
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning
M Assran, J Romoff, N Ballas, J Pineau, M Rabbat
Advances in Neural Information Processing Systems, 13299-13309, 2019
Separating value functions across time-scales
J Romoff, P Henderson, A Touati, E Brunskill, J Pineau, Y Ollivier
International Conference on Machine Learning, 5468-5477, 2019
Multi-advisor reinforcement learning
R Laroche, M Fatemi, J Romoff, H van Seijen
arXiv preprint arXiv:1704.00756, 2017
Direct behavior specification via constrained reinforcement learning
J Roy, R Girgis, J Romoff, PL Bacon, C Pal
arXiv preprint arXiv:2112.12228, 2021
Separation of concerns in reinforcement learning
H van Seijen, M Fatemi, J Romoff, R Laroche
arXiv preprint arXiv:1612.05159, 2016
TDprop: Does Adaptive Optimization With Jacobi Preconditioning Help Temporal Difference Learning?
J Romoff, P Henderson, D Kanaa, E Bengio, A Touati, PL Bacon, J Pineau
Proceedings of the 20th International Conference on Autonomous Agents and …, 2021
Graph augmented deep reinforcement learning in the gamerland3d environment
E Beeching, M Peter, P Marcotte, J Debangoye, O Simonin, J Romoff, ...
arXiv preprint arXiv:2112.11731, 2021
Deep conditional multi-task learning in atari
J Romoff, E Bengio, J Pineau
Workshop on Abstraction in Reinforcement Learning at ICML, 2016
Decomposing the Bellman Equation in Reinforcement Learning
J Romoff
McGill University (Canada), 2021
Improving Intrinsic Exploration by Creating Stationary Objectives
RC Castanyer, J Romoff, G Berseth
arXiv preprint arXiv:2310.18144, 2023
Learning Computational Efficient Bots with Costly Features
A Kobanda, CA Valliappan, J Romoff, L Denoyer
2023 IEEE Conference on Games (CoG), 1-8, 2023
Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play
D Bairamian, P Marcotte, J Romoff, G Robert, D Nowrouzezahrai
arXiv preprint arXiv:2311.17190, 2023
About the attractor phenomenon in decomposed reinforcement learning
R Laroche, M Fatemi, J Romoff, H van Seijen
The system can't perform the operation now. Try again later.
Articles 1–20