Follow
Paul Barde
Paul Barde
postdoc, UQO, UofA, Quebec AI institute (Mila)
Verified email at mila.quebec - Homepage
Title
Cited by
Cited by
Year
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 34, 2020
262020
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
252020
Regularized Inverse Reinforcement Learning
W Jeon, CY Su, P Barde, T Doan, D Nowrouzezahrai, J Pineau
International Conference on Learning Representations (ICLR) (Spotlight …, 2021
122021
Scalable and sample-efficient multi-agent imitation learning
W Jeon, P Barde, D Nowrouzezahrai, J Pineau
Proceedings of the Workshop on Reinforcement Learning in Games, co-located …, 2020
92020
Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic
W Jeon, P Barde, D Nowrouzezahrai, J Pineau
arXiv preprint arXiv:2002.10525, 2020
82020
Learning to guide and to be guided in the architect-builder problem
P Barde, T Karch, D Nowrouzezahrai, C Moulin-Frier, C Pal, PY Oudeyer
International Conference on Learning Representations (ICLR), 2021
52021
A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem
P Barde, J Foerster, D Nowrouzezahrai, A Zhang
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023
22023
The system can't perform the operation now. Try again later.
Articles 1–7