| Option-critic in cooperative multi-agent systems J Chakravorty, N Ward, J Roy, M Chevalier-Boisvert, S Basu, A Lupu, ... arXiv preprint arXiv:1911.12825, 2019 | 35 | 2019 |
| Direct behavior specification via constrained reinforcement learning J Roy, R Girgis, J Romoff, PL Bacon, C Pal arXiv preprint arXiv:2112.12228, 2021 | 34 | 2021 |
| Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning J Roy, P Barde, F Harvey, D Nowrouzezahrai, C Pal Advances in Neural Information Processing Systems 33, 2020 | 28 | 2020 |
| Adversarial soft advantage fitting: Imitation learning without policy optimization P Barde, J Roy, W Jeon, J Pineau, C Pal, D Nowrouzezahrai Advances in Neural Information Processing Systems 33, 12334-12344, 2020 | 27 | 2020 |
| Recurrent semi-supervised classification and constrained adversarial generation with motion capture data FG Harvey, J Roy, D Kanaa, C Pal Image and Vision Computing 78, 42-52, 2018 | 23* | 2018 |
| Sensitivity of MRI parameters within intervertebral discs to the severity of adolescent idiopathic scoliosis M Huber, G Gilbert, J Roy, S Parent, H Labelle, D Périé Journal of Magnetic Resonance Imaging 44 (5), 1123-1131, 2016 | 20 | 2016 |
| Goal-conditioned gflownets for controllable multi-objective molecular design J Roy, PL Bacon, C Pal, E Bengio arXiv preprint arXiv:2306.04620, 2023 | 6 | 2023 |
| Synflownet: Towards molecule design with guaranteed synthesis pathways M Cretu, C Harris, J Roy, E Bengio, P Liò arXiv preprint arXiv:2405.01155, 2024 | 2 | 2024 |
