Yannis Flet-Berliac

26 papers A* 8A 1Journal 16

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	ShiQ: Bringing back Bellman to LLMs. CoRR Pierre Clavier, Nathan Grinsztajn, Raphaël Avalos, Yannis Flet-Berliac, Irem Ergün, Omar Darwiche Domingues, Eugene Tarassov, Olivier Pietquin, Pierre H. Richemond, Florian Strub, Matthieu Geist
2024	J	`jnl`	Averaging log-likelihoods in direct alignment. CoRR Nathan Grinsztajn, Yannis Flet-Berliac, Mohammad Gheshlaghi Azar, Florian Strub, Bill Wu, Eugene Choi, Chris Cremer, Arash Ahmadian, Yash Chandak, Olivier Pietquin, Matthieu Geist
2024	J	`jnl`	Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier. CoRR John Dang, Shivalika Singh, Daniel D'souza, Arash Ahmadian, Alejandro Salamanca, Madeline Smith, Aidan Peppin, Sungjin Hong, Manoj Govindassamy, Terrence Zhao, Sandra Kublik, Meor Amer, Viraat Aryabumi, Jon Ander Campos, Yi Chern Tan, Tom Kocmi, Florian Strub, Nathan Grinsztajn, Yannis Flet-Berliac, Acyr Locatelli, Hangyu Lin, Dwarak Talupuru, Bharat Venkitesh, David Cairuz, Bowen Yang, Tim Chung, Wei-Yin Ko, Sylvie Shang Shi, Amir Shukayev, Sammie Bae, Aleksandra Piktus, Roman Castagné, Felipe Cruz-Salinas, Eddie Kim, Lucas Crawhall-Stein, Adrien Morisot, Sudip Roy, Phil Blunsom, Ivan Zhang, Aidan N. Gomez, Nick Frosst, Marzieh Fadaee, Beyza Ermis, Ahmet Üstün, Sara Hooker
2024	A*	`conf`	Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion. EMNLP Yannis Flet-Berliac, Nathan Grinsztajn, Florian Strub, Eugene Choi, Bill Wu, Chris Cremer, Arash Ahmadian, Yash Chandak, Mohammad Gheshlaghi Azar, Olivier Pietquin, Matthieu Geist
2024	J	`jnl`	Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion. CoRR Yannis Flet-Berliac, Nathan Grinsztajn, Florian Strub, Eugene Choi, Chris Cremer, Arash Ahmadian, Yash Chandak, Mohammad Gheshlaghi Azar, Olivier Pietquin, Matthieu Geist
2024	A*	`conf`	OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators. NeurIPS Allen Nie, Yash Chandak, Christina J. Yuan, Anirudhan Badrinath, Yannis Flet-Berliac, Emma Brunskill
2024	J	`jnl`	OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators. CoRR Allen Nie, Yash Chandak, Christina J. Yuan, Anirudhan Badrinath, Yannis Flet-Berliac, Emma Brunskill
2024	J	`jnl`	PASTA: Pretrained Action-State Transformer Agents. RLJ Raphaël Boige, Yannis Flet-Berliac, Lars C. P. M. Quaedvlieg, Arthur Flajolet, Guillaume Richard, Thomas Pierrot
2023	A*	`conf`	Model-Based Offline Reinforcement Learning with Local Misspecification. AAAI Kefan Dong, Yannis Flet-Berliac, Allen Nie, Emma Brunskill
2023	J	`jnl`	Model-based Offline Reinforcement Learning with Local Misspecification. CoRR Kefan Dong, Yannis Flet-Berliac, Allen Nie, Emma Brunskill
2023	J	`jnl`	PASTA: Pretrained Action-State Transformer Agents. CoRR Raphaël Boige, Yannis Flet-Berliac, Arthur Flajolet, Guillaume Richard, Thomas Pierrot
2023	A*	`conf`	Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets. NeurIPS Anirudhan Badrinath, Yannis Flet-Berliac, Allen Nie, Emma Brunskill
2023	J	`jnl`	Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets. CoRR Anirudhan Badrinath, Yannis Flet-Berliac, Allen Nie, Emma Brunskill
2022	A*	`conf`	Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data. NeurIPS Allen Nie, Yannis Flet-Berliac, Deon R. Jordan, William Steenbergen, Emma Brunskill
2022	J	`jnl`	Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data. CoRR Allen Nie, Yannis Flet-Berliac, Deon R. Jordan, William Steenbergen, Emma Brunskill
2022	J	`jnl`	Offline Policy Optimization with Eligible Actions. CoRR Yao Liu, Yannis Flet-Berliac, Emma Brunskill
2022	A	`conf`	Offline policy optimization with eligible actions. UAI Yao Liu, Yannis Flet-Berliac, Emma Brunskill
2022	J	`jnl`	SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics. CoRR Yannis Flet-Berliac, Debabrota Basu
2021	A*	`conf`	Adversarially Guided Actor-Critic. ICLR Yannis Flet-Berliac, Johan Ferret, Olivier Pietquin, Philippe Preux, Matthieu Geist
2021	J	`jnl`	Adversarially Guided Actor-Critic. CoRR Yannis Flet-Berliac, Johan Ferret, Olivier Pietquin, Philippe Preux, Matthieu Geist
2021	A*	`conf`	Learning Value Functions in Deep Policy Gradients using Residual Variance. ICLR Yannis Flet-Berliac, Reda Ouhamma, Odalric-Ambrym Maillard, Philippe Preux
2021	—	`—`	Sample-Efficient Deep Reinforcement Learning for Control, Exploration and Safety. (Apprentissage par renforcement profond éfficace pour le contrôle, l'exploration et la sûreté). Yannis Flet-Berliac
2020	J	`jnl`	Is Standard Deviation the New Standard? Revisiting the Critic in Deep Policy Gradients. CoRR Yannis Flet-Berliac, Reda Ouhamma, Odalric-Ambrym Maillard, Philippe Preux
2020	A*	`conf`	Only Relevant Information Matters: Filtering Out Noisy Samples To Boost RL. IJCAI Yannis Flet-Berliac, Philippe Preux
2019	J	`jnl`	High-Dimensional Control Using Generalized Auxiliary Tasks. CoRR Yannis Flet-Berliac, Philippe Preux
2019	J	`jnl`	Samples are not all useful: Denoising policy gradient updates using variance. CoRR Yannis Flet-Berliac, Philippe Preux