Grégoire Delétang

25 papers A* 8Journal 16Unranked 1
YearRankTypeTitle / Venue / Authors
2024 A* conf
Amortized Planning with Large-Scale Transformers: A Case Study on Chess.
NeurIPS
Anian Ruoss, Grégoire Delétang, Sourabh Medapati, Jordi Grau-Moya, Kevin Li, Elliot Catt, John Reid, Cannada A. Lewis, Joel Veness, Tim Genewein
2024 A* conf
Distributional Bellman Operators over Mean Embeddings.
ICML
Li Kevin Wenliang, Grégoire Delétang, Matthew Aitchison, Marcus Hutter, Anian Ruoss, Arthur Gretton, Mark Rowland
2024 J jnl
Evaluating Frontier Models for Dangerous Capabilities.
CoRR
Mary Phuong, Matthew Aitchison, Elliot Catt, Sarah Cogan, Alexandre Kaskasoli, Victoria Krakovna, David Lindner, Matthew Rahtz, Yannis Assael, Sarah Hodkinson, Heidi Howard, Tom Lieberum, Ramana Kumar, Maria Abi Raad, Albert Webson, Lewis Ho, Sharon Lin, Sebastian Farquhar, Marcus Hutter, Grégoire Delétang, Anian Ruoss, Seliem El-Sayed, Sasha Brown, Anca D. Dragan, Rohin Shah, Allan Dafoe, Toby Shevlane
2024 J jnl
Grandmaster-Level Chess Without Search.
CoRR
Anian Ruoss, Grégoire Delétang, Sourabh Medapati, Jordi Grau-Moya, Li Kevin Wenliang, Elliot Catt, John Reid, Tim Genewein
2024 A* conf
Language Modeling Is Compression.
ICLR
Grégoire Delétang, Anian Ruoss, Paul-Ambroise Duquenne, Elliot Catt, Tim Genewein, Christopher Mattern, Jordi Grau-Moya, Li Kevin Wenliang, Matthew Aitchison, Laurent Orseau, Marcus Hutter, Joel Veness
2024 A* conf
Learning Universal Predictors.
ICML
Jordi Grau-Moya, Tim Genewein, Marcus Hutter, Laurent Orseau, Grégoire Delétang, Elliot Catt, Anian Ruoss, Li Kevin Wenliang, Christopher Mattern, Matthew Aitchison, Joel Veness
2024 J jnl
Learning Universal Predictors.
CoRR
Jordi Grau-Moya, Tim Genewein, Marcus Hutter, Laurent Orseau, Grégoire Delétang, Elliot Catt, Anian Ruoss, Li Kevin Wenliang, Christopher Mattern, Matthew Aitchison, Joel Veness
2023 J jnl
Distributional Bellman Operators over Mean Embeddings.
CoRR
Li Kevin Wenliang, Grégoire Delétang, Matthew Aitchison, Marcus Hutter, Anian Ruoss, Arthur Gretton, Mark Rowland
2023 J jnl
Language Modeling Is Compression.
CoRR
Grégoire Delétang, Anian Ruoss, Paul-Ambroise Duquenne, Elliot Catt, Tim Genewein, Christopher Mattern, Jordi Grau-Moya, Li Kevin Wenliang, Matthew Aitchison, Laurent Orseau, Marcus Hutter, Joel Veness
2023 A* conf
Memory-Based Meta-Learning on Non-Stationary Distributions.
ICML
Tim Genewein, Grégoire Delétang, Anian Ruoss, Li Kevin Wenliang, Elliot Catt, Vincent Dutordoir, Jordi Grau-Moya, Laurent Orseau, Marcus Hutter, Joel Veness
2023 J jnl
Memory-Based Meta-Learning on Non-Stationary Distributions.
CoRR
Tim Genewein, Grégoire Delétang, Anian Ruoss, Li Kevin Wenliang, Elliot Catt, Vincent Dutordoir, Jordi Grau-Moya, Laurent Orseau, Marcus Hutter, Joel Veness
2023 A* conf
Neural Networks and the Chomsky Hierarchy.
ICLR
Grégoire Delétang, Anian Ruoss, Jordi Grau-Moya, Tim Genewein, Li Kevin Wenliang, Elliot Catt, Chris Cundy, Marcus Hutter, Shane Legg, Joel Veness, Pedro A. Ortega
2023 — conf
Randomized Positional Encodings Boost Length Generalization of Transformers.
ACL (2)
Anian Ruoss, Grégoire Delétang, Tim Genewein, Jordi Grau-Moya, Róbert Csordás, Mehdi Bennani, Shane Legg, Joel Veness
2023 J jnl
Randomized Positional Encodings Boost Length Generalization of Transformers.
CoRR
Anian Ruoss, Grégoire Delétang, Tim Genewein, Jordi Grau-Moya, Róbert Csordás, Mehdi Bennani, Shane Legg, Joel Veness
2023 A* conf
Self-Predictive Universal AI.
NeurIPS
Elliot Catt, Jordi Grau-Moya, Marcus Hutter, Matthew Aitchison, Tim Genewein, Grégoire Delétang, Kevin Li, Joel Veness
2022 J jnl
Beyond Bayes-optimality: meta-learning what you know you don't know.
CoRR
Jordi Grau-Moya, Grégoire Delétang, Markus Kunesch, Tim Genewein, Elliot Catt, Kevin Li, Anian Ruoss, Chris Cundy, Joel Veness, Jane X. Wang, Marcus Hutter, Christopher Summerfield, Shane Legg, Pedro A. Ortega
2022 J jnl
Neural Networks and the Chomsky Hierarchy.
CoRR
Grégoire Delétang, Anian Ruoss, Jordi Grau-Moya, Tim Genewein, Li Kevin Wenliang, Elliot Catt, Marcus Hutter, Shane Legg, Pedro A. Ortega
2022 J jnl
Your Policy Regularizer is Secretly an Adversary.
CoRR
Rob Brekelmans, Tim Genewein, Jordi Grau-Moya, Grégoire Delétang, Markus Kunesch, Shane Legg, Pedro A. Ortega
2022 J jnl
Your Policy Regularizer is Secretly an Adversary.
Trans. Mach. Learn. Res.
Rob Brekelmans, Tim Genewein, Jordi Grau-Moya, Grégoire Delétang, Markus Kunesch, Shane Legg, Pedro A. Ortega
2021 J jnl
Causal Analysis of Agent Behavior for AI Safety.
CoRR
Grégoire Delétang, Jordi Grau-Moya, Miljan Martic, Tim Genewein, Tom McGrath, Vladimir Mikulik, Markus Kunesch, Shane Legg, Pedro A. Ortega
2021 J jnl
Model-Free Risk-Sensitive Reinforcement Learning.
CoRR
Grégoire Delétang, Jordi Grau-Moya, Markus Kunesch, Tim Genewein, Rob Brekelmans, Shane Legg, Pedro A. Ortega
2021 J jnl
Shaking the foundations: delusions in sequence models for interaction and control.
CoRR
Pedro A. Ortega, Markus Kunesch, Grégoire Delétang, Tim Genewein, Jordi Grau-Moya, Joel Veness, Jonas Buchli, Jonas Degrave, Bilal Piot, Julien Pérolat, Tom Everitt, Corentin Tallec, Emilio Parisotto, Tom Erez, Yutian Chen, Scott E. Reed, Marcus Hutter, Nando de Freitas, Shane Legg
2020 J jnl
Algorithms for Causal Reasoning in Probability Trees.
CoRR
Tim Genewein, Tom McGrath, Grégoire Delétang, Vladimir Mikulik, Miljan Martic, Shane Legg, Pedro A. Ortega
2020 A* conf
Meta-trained agents implement Bayes-optimal agents.
NeurIPS
Vladimir Mikulik, Grégoire Delétang, Tom McGrath, Tim Genewein, Miljan Martic, Shane Legg, Pedro A. Ortega
2020 J jnl
Meta-trained agents implement Bayes-optimal agents.
CoRR
Vladimir Mikulik, Grégoire Delétang, Tom McGrath, Tim Genewein, Miljan Martic, Shane Legg, Pedro A. Ortega