A new framework for distributed reinforcement learning
3 Mins read
Overall, the high-level goals of Acme are as follows: To enable the reproducibility of our methods and results — this will help…
Software and Tasks for Continuous Control
2 Mins read
Overview A public colab notebook with a tutorial for dm_control software is available here. Infrastructure An autogenerated MuJoCo Python wrapper provides full…
Applying for technical roles
6 Mins read
It’s no secret that the gender gap still exists within STEM. Despite a slight increase in recent years, studies show that women…
Benchmarks for Offline Reinforcement Learning
1 Mins read
Many of the successes of RL rely heavily on repeated online interactions of an agent with an environment, which we call online…
Traffic prediction with advanced Graph Neural Networks
7 Mins read
By partnering with Google, DeepMind is able to bring the benefits of AI to billions of people all over the world. From…
Fast reinforcement learning through the composition of behaviours
14 Mins read
The compositional nature of intelligence Imagine if you had to learn how to chop, peel and stir all over again every time…
Meet Otter: A Cutting-Edge AI Model that Leverages a Large-Scale Dataset Called MIMIC-IT to Achieve State-of-the-Art Performances in Perception and Reasoning Benchmarks
3 Mins read
Multi-faceted models strive to integrate data from diverse sources, including written language, pictures, and videos, to execute various functions. These models have…
Quantum Physics and Chemistry from First Principles
11 Mins read
In an article recently published in Physical Review Research, we show how deep learning can help solve the fundamental equations of quantum…
Breaking down global barriers to access
3 Mins read
This week, we welcomed our biggest and most geographically diverse cohort of DeepMind scholars yet. We’re excited to reflect on the journey…
Using Unity to Help Solve Intelligence
3 Mins read
A wide range of environments In the pursuit of artificial general intelligence (AGI), we seek to create agents that can achieve goals…