Follow
Grégoire Delétang
Grégoire Delétang
Google DeepMind
Verified email at google.com
Title
Cited by
Cited by
Year
Neural Networks and the Chomsky Hierarchy
G Delétang, A Ruoss, J Grau-Moya, T Genewein, LK Wenliang, E Catt, ...
International Conference on Learning Representations 11, 2022
712022
Shaking the foundations: delusions in sequence models for interaction and control
PA Ortega, M Kunesch, G Delétang, T Genewein, J Grau-Moya, J Veness, ...
arXiv preprint arXiv:2110.10819, 2021
412021
Meta-trained agents implement Bayes-Optimal agents
V Mikulik, G Delétang, T McGrath, T Genewein, M Martic, S Legg, ...
Advances in Neural Information Processing Systems 33, 2020
362020
Language Modeling is Compression
G Delétang, A Ruoss, PA Duquenne, E Catt, T Genewein, C Mattern, ...
International Conference on Learning Representations 12, 2023
342023
Randomized Positional Encodings Boost Length Generalization of Transformers
A Ruoss, G Delétang, T Genewein, J Grau-Moya, R Csordás, M Bennani, ...
61st Annual Meeting of the Association for Computational Linguistics, 2023
332023
Algorithms for causal reasoning in probability trees
T Genewein, T McGrath, G Delétang, V Mikulik, M Martic, S Legg, ...
arXiv preprint arXiv:2010.12237, 2020
162020
Model-free risk-sensitive reinforcement learning
G Delétang, J Grau-Moya, M Kunesch, T Genewein, R Brekelmans, ...
arXiv preprint arXiv:2111.02907, 2021
112021
Causal Analysis of Agent Behavior for AI Safety
G Déletang, J Grau-Moya, M Martic, T Genewein, T McGrath, V Mikulik, ...
arXiv preprint arXiv:2103.03938, 2021
102021
Your policy regularizer is secretly an adversary
R Brekelmans, T Genewein, J Grau-Moya, G Delétang, M Kunesch, ...
arXiv preprint arXiv:2203.12592, 2022
92022
Memory-Based Meta-Learning on Non-Stationary Distributions
T Genewein, G Delétang, A Ruoss, LK Wenliang, E Catt, V Dutordoir, ...
International Conference on Machine Learning 40, 2023
52023
Grandmaster-level chess without search
A Ruoss, G Delétang, S Medapati, J Grau-Moya, LK Wenliang, E Catt, ...
arXiv preprint arXiv:2402.04494, 2024
32024
Beyond Bayes-optimality: meta-learning what you know you don't know
J Grau-Moya, G Delétang, M Kunesch, T Genewein, E Catt, K Li, A Ruoss, ...
arXiv preprint arXiv:2209.15618, 2022
22022
Evaluating Frontier Models for Dangerous Capabilities
M Phuong, M Aitchison, E Catt, S Cogan, A Kaskasoli, V Krakovna, ...
arXiv preprint arXiv:2403.13793, 2024
2024
Learning Universal Predictors
J Grau-Moya, T Genewein, M Hutter, L Orseau, G Delétang, E Catt, ...
arXiv preprint arXiv:2401.14953, 2024
2024
Distributional Bellman Operators over Mean Embeddings
LK Wenliang, G Déletang, M Aitchison, M Hutter, A Ruoss, A Gretton, ...
arXiv preprint arXiv:2312.07358, 2023
2023
Self-Predictive Universal AI
E Catt, J Grau-Moya, M Hutter, M Aitchison, T Genewein, G Deletang, ...
Advances in Neural Information Processing Systems 37, 2023
2023
Policy Gradient without Boostrapping via Truncated Value Learning
M Aitchison, P Sweetser, G Deletang, M Hutter
2023
Generative Reinforcement Learning with Transformers
G Deletang, A Ruoss, LK Wenliang, E Catt, T Genewein, J Grau-Moya, ...
2023
The system can't perform the operation now. Try again later.
Articles 1–18