Matthieu Geist

papers

1,352

total citations

papers (15)

Twice regularized MDPs and the equivalence between robustness and regularization

NEURIPS 2021arXiv

citations

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

NEURIPS 2023arXiv

citations

Policy Gradient for Rectangular Robust Markov Decision Processes

NEURIPS 2023arXiv

citations

Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.

ICLR 2024arXiv

citations

There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning

NEURIPS 2021arXiv

citations

Learning Energy Networks with Generalized Fenchel-Young Losses

NEURIPS 2022arXiv

citations

On Imitation in Mean-field Games

NEURIPS 2023arXiv

citations

Learning Discrete-Time Major-Minor Mean Field Games

AAAI 2024arXiv

citations

ShiQ: Bringing back Bellman to LLMs

NEURIPS 2025arXiv

citations

Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning

NEURIPS 2020

citations

Matthieu Geist

papers (15)

MusicRL: Aligning Music Generation to Human Preferences

Nash Learning from Human Feedback

Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications

Munchausen Reinforcement Learning

What Matters for Adversarial Imitation Learning?

Twice regularized MDPs and the equivalence between robustness and regularization

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

Policy Gradient for Rectangular Robust Markov Decision Processes

Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.

There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning

Learning Energy Networks with Generalized Fenchel-Young Losses

On Imitation in Mean-field Games

Learning Discrete-Time Major-Minor Mean Field Games

ShiQ: Bringing back Bellman to LLMs

Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning

papers (15)

MusicRL: Aligning Music Generation to Human Preferences

Nash Learning from Human Feedback

Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications

Munchausen Reinforcement Learning

What Matters for Adversarial Imitation Learning?

Twice regularized MDPs and the equivalence between robustness and regularization

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

Policy Gradient for Rectangular Robust Markov Decision Processes

Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.

There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning

Learning Energy Networks with Generalized Fenchel-Young Losses

On Imitation in Mean-field Games

Learning Discrete-Time Major-Minor Mean Field Games

ShiQ: Bringing back Bellman to LLMs

Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning