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 Science, we present new developments in reinforcement learning, resulting in human-level performance in Quake III Arena Capture the Flag. This is a complex, multi-agent environment and one of the canonical 3D first-person multiplayer games. The agents successfully cooperate with both artificial and human teammates, and demonstrate high performance even when trained with reaction times comparable to human players. Furthermore, we show how these methods have managed to scale beyond research Capture the Flag environments to the full game of Quake III Arena.
Senior Research Scientist
Raia is a Senior Research Scientist working on Deep Learning at DeepMind, with a particular focus on solving robotics and navigation using deep neural networks. She joined DeepMind following positions at Carnegie Mellon and SRI International as she saw the combination of research into games, neuroscience, deep learning and reinforcement learning as a unique proposition that could lead to fundamental breakthroughs in AI. She says that one of her favourite moments at DeepMind was watching the livestream of Lee Sedol playing AlphaGo at 4am surrounded by the rest of the team, despite the difference in timezone!
Senior Research Scientist
Shakir grew up in Johannesburg, South Africa, and initially pursued a degree in electrical and information engineering before becoming intrigued by the principles of learning systems and moving onto graduate study at Cambridge University and the Canadian Institute for Advanced Research (CIFAR) exploring Neural Computation and Adaptive Perception. He then joined DeepMind as a Research Scientist, exploring the fundamentals of imagination, reasoning, and future thinking without the need for external signals. He loves working at DeepMind because of its unique environment that embraces and encourages different approaches to machine learning, and relishes the opportunity to regularly think about the ways in which machine learning and AI can be used to truly overcome the challenges facing humanity.
Mihaela is a Research Engineer at DeepMind. She joined us in 2016 after becoming fascinated with machine learning during her degree at Imperial College London. Before joining DeepMind to research generative models, she worked on text understanding and tackling natural language problems at Google. Mihaela says that for anyone with broad research interests, DeepMind is “an oasis of inspiration and knowledge, with plenty of world experts to learn from and flexibility to dive into a variety of topics”.
Avishkar spent six years as a software engineer in his native country of South Africa before moving into the field of machine learning and completing a masters at University College London. As a Research Engineer at DeepMind he focuses on the technical implementation of machine learning projects, helping Research Scientists turn their ideas into reality. He says the role “provides the ideal balance between technical coding and research”. He has worked in a variety of research areas and loves the atmosphere at DeepMind as well as being able to interact with so many leaders in the field.
Irina joined DeepMind’s neuroscience team in 2015 following a PhD at Oxford University. Her work takes inspiration from the way that babies learn from the world around them, using unsupervised interactions with the environment, copying others, and testing new hypotheses. By developing AI methods that can do this she hopes to create far more capable, resilient algorithms that can adapt to new challenges and perform a larger number of tasks. She joined DeepMind as it gave her a huge amount of freedom to work on the ideas she is passionate about in an “inspirational, incredible” environment – a “heaven for AI geeks.”
Dominik is a Software Engineer in the Research Engineering team. He joined DeepMind from Google in August 2014, where he worked on Chrome for Android. Dominik’s role focuses on the performance of our algorithms. This involves writing tools and libraries for our researchers to scale up their experiments and help them to run their algorithms as fast as possible. Dominik joined DeepMind because he wanted to be a part of an “incredibly exciting mission which could have an immediate and clear impact”. One of his most memorable DeepMind experiences was seeing WaveNet go from research project to reality.