image: Illustration of agents playing Capture the Flag, showing a range of behaviors. This material relates to a paper that appeared in the May 31,2019 issue of Science, published by AAAS. The paper, by M. Jaderberg at DeepMind in London, UK, and colleagues was titled, 'Human-level performance in 3D multiplayer games with population-based reinforcement learning.' view more
Credit: DeepMind