Volodymyr Mnih

Computer scientist who, as a researcher at DeepMind, was lead author of the deep Q-networkdeep Q-network, n.: A method, made famous by DeepMind in 2013–2015, in which a neural network learned to play dozens of Atari video games from screen pixels and the score alone, many at human level. (DQN) papers that launched deep reinforcement learningdeep reinforcement learning, n.: Reinforcement learning in which a large neural network does the learning, letting an AI learn tasks such as video games or robot control directly from raw inputs like screen pixels or camera images.. After a PhD with Geoffrey HintonGeoffrey Hinton, prop. n.: A British-Canadian scientist whose decades of persistent work on brain-inspired neural networks laid the foundations of modern AI; often called a 'godfather of AI', he now warns publicly about its dangers. at the University of Toronto, he showed in 'Playing Atari with Deep Reinforcement Learning' (2013) that a convolutional neural networkconvolutional neural network, n.: A kind of neural network built for images and other grid-like data. It slides small pattern detectors across the input, finding edges first, then shapes, then whole objects. trained by Q-learningQ-learning, n.: A trial-and-error method in which an agent keeps a score for every move in every situation and nudges each score toward the reward it got plus the best score available next. directly from screen pixels could learn several Atari games. The 2015 Nature paper extended the agent to 49 games of the Arcade Learning EnvironmentArcade Learning Environment, prop. n.: A software platform that lets AI programs play classic Atari 2600 video games, used since 2012 as a standard test of how well one AI can learn many different tasks from screen images., reaching human-level scores on many with a single architecture and set of hyperparameters, stabilized by experience replayexperience replay, n.: Storing an AI agent's past experiences in a memory bank and repeatedly learning from random samples of them, rather than only from what just happened. and a target networktarget network, n.: A slowly updated copy of an AI agent's learning network, used to compute the goals it learns toward, so those goals do not shift every time the network changes.. Published a year after Google acquired DeepMind, the result made deep reinforcement learning a major field and set the stage for AlphaGoAlphaGo, prop. n.: A DeepMind program that in 2016 beat Lee Sedol, one of the world's best players of the board game Go, a decade or more before many experts expected a computer to manage it.. He also introduced asynchronous advantage actor–criticA3C, abbr.: A 2016 DeepMind training method in which many copies of an AI agent learn in parallel on separate copies of a task, pooling their updates into one shared neural network. (A3C, 2016), which trained many agents in parallel on ordinary processors, and an early neural model of visual attention (2014).