-
Research
Unsupervised learning: The curious pupil
Over the last decade, machine learning has made unprecedented progress in areas as diverse as image recognition, self-driving cars and playing complex games like Go. These successes have been...
-
Research
Capture the Flag: the emergence of complex cooperative agents
Mastering the strategy, tactical understanding, and team play involved in multiplayer video games represents a critical challenge for AI research. In our latest paper, now published in the journal...
-
Research
Identifying and eliminating bugs in learned predictive models
Bugs and software have gone hand in hand since the beginning of computer programming. Over time, software developers have established a set of best practices for testing and debugging before...
-
Research
TF-Replicator: Distributed Machine Learning for Researchers
At DeepMind, the Research Platform Team builds infrastructure to empower and accelerate our AI research. Today, we are excited to share how we developed TF-Replicator, a software library that...
-
Research
Machine learning can boost the value of wind energy
Carbon-free technologies like renewable energy help combat climate change, but many of them have not reached their full potential. Consider wind power: over the past decade, wind farms have become...
-
Research
AlphaStar: Mastering the real-time strategy game StarCraft II
Games have been used for decades as an important way to test and evaluate the performance of artificial intelligence systems. As capabilities have increased, the research community has sought...
-
Research
AlphaZero: Shedding new light on chess, shogi, and Go
In late 2017 we introduced AlphaZero, a single system that taught itself from scratch how to master the games of chess, shogi (Japanese chess), and Go, beating a world-champion program in each...
-
Research
Open sourcing TRFL: a library of reinforcement learning building blocks
Today we are open sourcing a new library of useful building blocks for writing reinforcement learning (RL) agents in TensorFlow. Named TRFL (pronounced ‘truffle’), it represents a collection of...
-
Research
Preserving Outputs Precisely while Adaptively Rescaling Targets
Multi-task learning - allowing a single agent to learn how to solve many different tasks - is a longstanding objective for artificial intelligence research. Recently, there has been a lot of...
-
Research
Objects that Sound
Visual and audio events tend to occur together: a musician plucking guitar strings and the resulting melody; a wine glass shattering and the accompanying crash; the roar of a motorcycle as it...
-
Research
Measuring abstract reasoning in neural networks
Neural network-based models continue to achieve impressive results on longstanding machine learning problems, but establishing their capacity to reason about abstract concepts has proven...
-
Research
DeepMind papers at ICML 2018
The 2018 International Conference on Machine Learning will take place in Stockholm, Sweden from 10-15 July. For those attending and planning the week ahead, we are sharing a schedule of DeepMind...