Théophane Weber

DeepMind (United Kingdom) — United Kingdom

Computer Science · Physical Sciences

22h-index2.9kcitations80works0.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(37), Artificial Intelligence in Games(13), Neural dynamics and brain function(7), AI-based Problem Solving and Planning(7), Bayesian Modeling and Causal Inference(7)

Publications80 total

Drums of high width
arXiv (Cornell University)·2025Open Access
Drums of high width
Proceedings of the London Mathematical Society·2025· 1 cited
Advancing Geometry with AI: Multi-agent Generation of Polytopes
arXiv (Cornell University)·2025Open Access
DiscoGen: Learning to Discover Gene Regulatory Networks
arXiv (Cornell University)·2023Open Access
DiscoGen: Learning to Discover Gene Regulatory Networks
2023· 1 citedOpen Access
Equivariant MuZero
arXiv (Cornell University)·2023Open Access
Investigating the role of model-based learning in exploration and transfer
arXiv (Cornell University)·2023· 3 citedOpen Access
Laser: Latent Set Representations for 3D Generative Modeling
arXiv (Cornell University)·2023Open Access
Large-Scale Retrieval for Reinforcement Learning
arXiv (Cornell University)·2022· 11 citedOpen Access
Learning to Induce Causal Structure
arXiv (Cornell University)·2022· 17 citedOpen Access
Automatic Report-Based Labelling of Clinical EEGs for Classifier Training
2021· 6 cited
Procedural Generalization by Planning with Self-Supervised World Models
arXiv (Cornell University)·2021· 4 citedOpen Access
Divide-and-Conquer Monte Carlo Tree Search
2021
Model-Free Counterfactual Credit Assignment
2021
On the role of planning in model-based deep reinforcement learning
arXiv (Cornell University)·2021· 26 citedOpen Access
Muesli: Combining Improvements in Policy Optimization
arXiv (Cornell University)·2021· 12 citedOpen Access
Synthetic Returns for Long-Term Credit Assignment
arXiv (Cornell University)·2021· 11 citedOpen Access
Neural Recursive Belief States in Multi-Agent Reinforcement Learning
arXiv (Cornell University)·2021· 7 citedOpen Access
A case for new neural network smoothness constraints
arXiv (Cornell University)·2020· 16 citedOpen Access
Counterfactual Credit Assignment in Model-Free Reinforcement Learning
arXiv (Cornell University)·2020· 8 citedOpen Access
page 1 of 4Next →

Frequent Co-authors

Lars Buesing(17), Nicolas Heess(12), Arthur Guez(11), Daan Wierstra(9), Peter Battaglia(9), Danilo Jimenez Rezende(8), Fabio Viola(8), Oriol Vinyals(7), Sébastien Racanière(6), Razvan Pascanu(6), David Silver(6), Jessica B. Hamrick(6), S. M. Ali Eslami(5), David Reichert(5), Demis Hassabis(5), Timothy Lillicrap(5), Frederic Besse(4), Karol Gregor(4), Adam Santoro(4), Justin Dauwels(4)