• Publications
  • Influence
Teaching Machines to Read and Comprehend
TLDR
A new methodology is defined that resolves this bottleneck and provides large scale supervised reading comprehension data that allows a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure to be developed.
Conditional Image Generation with PixelCNN Decoders
TLDR
The gated convolutional layers in the proposed model improve the log-likelihood of PixelCNN to match the state-of-the-art performance of PixelRNN on ImageNet, with greatly reduced computational cost.
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
TLDR
A new distributed agent IMPALA (Importance Weighted Actor-Learner Architecture) is developed that not only uses resources more efficiently in single-machine training but also scales to thousands of machines without sacrificing data efficiency or resource utilisation.
Neural Machine Translation in Linear Time
TLDR
The ByteNet decoder attains state-of-the-art performance on character-level language modelling and outperforms the previous best results obtained with recurrent networks and the latent alignment structure contained in the representations reflects the expected alignment between the tokens.
Google Research Football: A Novel Reinforcement Learning Environment
TLDR
The Google Research Football Environment is introduced, a new reinforcement learning environment where agents are trained to play football in an advanced, physics-based 3D simulator and it is available under a permissive open-source license.
Multi-task Deep Reinforcement Learning with PopArt
TLDR
This work proposes to automatically adapt the contribution of each task to the agent’s updates, so that all tasks have a similar impact on the learning dynamics, and learns a single trained policy that exceeds median human performance on this multi-task domain.
MetNet: A Neural Weather Model for Precipitation Forecasting
TLDR
This work introduces MetNet, a neural network that forecasts precipitation up to 8 hours into the future at the high spatial resolution of 1 km$^2$ and at the temporal resolution of 2 minutes with a latency in the order of seconds, and finds that MetNet outperforms Numerical Weather Prediction at forecasts of up to 7 to8 hours on the scale of the continental United States.
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference
TLDR
A modern scalable reinforcement learning agent called SEED (Scalable, Efficient Deep-RL), which is able to train on millions of frames per second and lower the cost of experiments compared to current methods with a simple architecture.
Boosting Search Engines with Interactive Agents
TLDR
A novel way of generating synthetic search sessions, which leverages the power of transformerbased language models through (self-)supervised learning, and presents a reinforcement learning agent with dynamically constrained actions that learns interactive search strategies from scratch.
Skillful Twelve Hour Precipitation Forecasts using Large Context Neural Networks
TLDR
A neural network is presented that is capable of large-scale precipitation forecasting up to twelve hours ahead and, starting from the same atmospheric state, the model achieves greater skill than the state-of-the-art physics-based models HRRR and HREF that currently operate in the Continental United States.
...
1
2
...