Solving intelligence to advance science and benefit humanity

Find out more
Representation of the interior of a tokamak
Research
Building safer dialogue agents
September 22, 2022
Representation of the interior of a tokamak
Company
How our principles helped define AlphaFold’s release
September 14, 2022
Representation of the interior of a tokamak
Company
Maximising the impact of our breakthroughs
September 9, 2022
Representation of the interior of a tokamak
Life at DeepMind
My journey from DeepMind intern to mentor
September 8, 2022
Representation of the interior of a tokamak
Technical blog
In conversation with AI: building better language models
September 6, 2022
Representation of the interior of a tokamak
Technical blog
From motor control to embodied intelligence
August 31, 2022
Paper
Publication
Constrained Offline RL via Stationary Distribution Correction Estimation
Paper
Publication
Optimizing Industrial Cooling Systems with Hierarchical Reinforcement Learning
Paper
Publication
Semi-analytical Industrial Cooling System Model for Reinforcement Learning
Paper
Publication
Generalised Policy Improvement with Geometric Policy Composition
Paper
Publication
From Dirichlet to Rubin: Optimistic exploration in RL without bonuses
Paper
Publication
Towards Coherent and Consistent Use of Entities in Narrative Generation