Friday, April 18, 2025

Deep Learning

When a passion for bass and brass helps build better tools

For our first Five Minutes With, we caught up with Kevin Millikin, a software engineer on the DevTools team. He's in Salt...

Performing multiple tasks using a single visual language model

One key aspect of intelligence is the ability to quickly learn how to perform a recent task given a brief instruction. For...

Choosing an Energetic Offline Policy

Reinforcement learning (RL) has made huge strides in recent years in solving real-world problems—and offline RL has made it even more practical....

Generalist Agent

Inspired by advances in large-scale language modeling, we take a similar approach to building a single generalist agent that goes beyond the...

Emergent Bartering Behavior in Multi-Agent Reinforcement Learning

IN our last articleWe investigate how populations of deep reinforcement learning (deep RL) agents can learn microeconomic behaviors such as the production,...

From LEGO Competitions to DeepMind Robotics Lab

Today's post is about Akhil Raj, a software engineer on the robotics team. We first met Akhil in Season 2 DeepMind: Podcastbut...

Sharing MuJoCo Source Code

In October 2021, we announced that we had acquired MuJoCo Physics Simulatorand made it freely available to everyone to support research everywhere....

Building a culture of responsible pioneering

How to Benefit Society with the Most Impactful Technology Developed TodayAs the COO of one of the world’s leading AI labs, I...