Koray Kavukcuoglu

Highly accurate protein structure prediction with AlphaFold

Abstract Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort ...

Human-level control through deep reinforcement learning

Mastering the game of Go with deep neural networks and tree search

Asynchronous Methods for Deep Reinforcement Learning

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network contro...

Reinforcement Learning with Unsupervised Auxiliary Tasks

Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possibl...

Highly accurate protein structure prediction for the human proteome