Monthly Archives: August 2017

DeepMind’s scientific mission is to push the boundaries of AI by developing systems that can learn to solve complex problems. To do this, we design agents and test their ability in a wide range of environments from the purpose-built DeepMind Lab to established games, such as Atari and Go.Testing our agents in games that are not specifically designed for AI research, and where humans play well, is crucial to benchmark agent performance. That is why we, along with our partner Blizzard Entertainment, are excited to announce the release of SC2LE, a set of tools that we hope will accelerate AI research in the real-time strategy game StarCraft II. The SC2LE release includes:A Machine Learning API developedby Blizzard that gives researchers and developers hooks into the game. This includes the release of tools for Linux for the first time.Adataset of anonymised game replays, which will increase from 65k to more than half a million in the coming weeks.An open source version of DeepMinds toolset, PySC2, to allow researchers to easily use Blizzards feature-layer API with their agents.A series of simple RL mini-games to allow researchers to test the performance of agents on specific tasks.A joint paperthat outlines the environment, and reports initial baseline results on the mini-games, supervised learning from replays, and the full 1v1 ladder game against the built-in AI.Read More

The second of our three-part series, which gives an overview of the papers we are presenting at the ICML 2017 Conference in Sydney, Australia.Read More

The final part of our three-part series that gives an overview of the papers we are presenting at the ICML 2017 Conference in Sydney, Australia.Read More

The first of our three-part series, which gives brief descriptions of the papers we are presenting at the ICML 2017 Conference in Sydney, Australia.Read More

Recent progress in AI has been remarkable.Artificial systems now outperform expert humans at Atari video games, the ancient board game Go, and high-stakes matches of heads-up poker. They can also produce handwriting and speech indistinguishable from those of humans, translate between multiple languages and even reformat your holiday snaps in the style of Van Gogh masterpieces.These advances are attributed to several factors, including the application of new statistical approaches and the increased processing power of computers. But in a recent Perspective in the journal Neuron, we argue that one often overlooked contribution is the use of ideas from experimental and theoretical neuroscience.Psychology and neuroscience have played a key role in the history of AI. Founding figures such as Donald Hebb, Warren McCulloch, Marvin Minsky and Geoff Hinton were all originally motivated by a desire to understand how the brain works. In fact, throughout the late 20th Century, much of the key work developing neural networks took place not in mathematics or physics labs, but in psychology and neurophysiology departments.Read More