Alert button
Picture for Matthieu Geist

Matthieu Geist

Alert button

On Imitation in Mean-field Games

Jun 26, 2023
Giorgia Ramponi, Pavel Kolev, Olivier Pietquin, Niao He, Mathieu Laurière, Matthieu Geist

Figure 1 for On Imitation in Mean-field Games
Figure 2 for On Imitation in Mean-field Games
Viaarxiv icon

GKD: Generalized Knowledge Distillation for Auto-regressive Sequence Models

Jun 23, 2023
Rishabh Agarwal, Nino Vieillard, Piotr Stanczyk, Sabela Ramos, Matthieu Geist, Olivier Bachem

Figure 1 for GKD: Generalized Knowledge Distillation for Auto-regressive Sequence Models
Figure 2 for GKD: Generalized Knowledge Distillation for Auto-regressive Sequence Models
Figure 3 for GKD: Generalized Knowledge Distillation for Auto-regressive Sequence Models
Figure 4 for GKD: Generalized Knowledge Distillation for Auto-regressive Sequence Models
Viaarxiv icon

Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback

May 31, 2023
Paul Roit, Johan Ferret, Lior Shani, Roee Aharoni, Geoffrey Cideron, Robert Dadashi, Matthieu Geist, Sertan Girgin, Léonard Hussenot, Orgad Keller, Nikola Momchev, Sabela Ramos, Piotr Stanczyk, Nino Vieillard, Olivier Bachem, Gal Elidan, Avinatan Hassidim, Olivier Pietquin, Idan Szpektor

Figure 1 for Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback
Figure 2 for Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback
Figure 3 for Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback
Figure 4 for Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback
Viaarxiv icon

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

May 26, 2023
Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen, Matthieu Geist, Yuejie Chi

Figure 1 for The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model
Figure 2 for The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model
Figure 3 for The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model
Viaarxiv icon

Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice

May 22, 2023
Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang, Nino Vieillard, Michal Valko, Wenhao Yang, Jincheng Mei, Pierre Ménard, Mohammad Gheshlaghi Azar, Rémi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvári, Wataru Kumagai, Yutaka Matsuo

Figure 1 for Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Figure 2 for Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Figure 3 for Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Figure 4 for Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Viaarxiv icon

Get Back Here: Robust Imitation by Return-to-Distribution Planning

May 02, 2023
Geoffrey Cideron, Baruch Tabanpour, Sebastian Curi, Sertan Girgin, Leonard Hussenot, Gabriel Dulac-Arnold, Matthieu Geist, Olivier Pietquin, Robert Dadashi

Figure 1 for Get Back Here: Robust Imitation by Return-to-Distribution Planning
Figure 2 for Get Back Here: Robust Imitation by Return-to-Distribution Planning
Figure 3 for Get Back Here: Robust Imitation by Return-to-Distribution Planning
Figure 4 for Get Back Here: Robust Imitation by Return-to-Distribution Planning
Viaarxiv icon

Twice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization

Mar 12, 2023
Esther Derman, Yevgeniy Men, Matthieu Geist, Shie Mannor

Figure 1 for Twice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization
Figure 2 for Twice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization
Figure 3 for Twice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization
Figure 4 for Twice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization
Viaarxiv icon

Towards Minimax Optimality of Model-based Robust Reinforcement Learning

Feb 10, 2023
Pierre Clavier, Erwan Le Pennec, Matthieu Geist

Figure 1 for Towards Minimax Optimality of Model-based Robust Reinforcement Learning
Viaarxiv icon

Policy Gradient for s-Rectangular Robust Markov Decision Processes

Jan 31, 2023
Navdeep Kumar, Esther Derman, Matthieu Geist, Kfir Levy, Shie Mannor

Figure 1 for Policy Gradient for s-Rectangular Robust Markov Decision Processes
Figure 2 for Policy Gradient for s-Rectangular Robust Markov Decision Processes
Figure 3 for Policy Gradient for s-Rectangular Robust Markov Decision Processes
Figure 4 for Policy Gradient for s-Rectangular Robust Markov Decision Processes
Viaarxiv icon

Extreme Q-Learning: MaxEnt RL without Entropy

Jan 05, 2023
Divyansh Garg, Joey Hejna, Matthieu Geist, Stefano Ermon

Figure 1 for Extreme Q-Learning: MaxEnt RL without Entropy
Figure 2 for Extreme Q-Learning: MaxEnt RL without Entropy
Figure 3 for Extreme Q-Learning: MaxEnt RL without Entropy
Figure 4 for Extreme Q-Learning: MaxEnt RL without Entropy
Viaarxiv icon