On Wednesday 23 May, the Department of Computer Science was delighted to celebrate the senior promotion of David Silver, Professor of Computer Science and Lead of the Reinforcement Learning Research Group at DeepMind.

To mark the occasion, David delivered his inaugural lecture on the topic of “Deep Reinforcement Learning: Mastering Games without Human Knowledge.” The event was attended by senior members of the Department, research students, and a number of distinguished academic and industry guests.

During the lecture, Professor Silver presented on current work at DeepMind on Artificial Intelligence, to achieve superhuman performance in challenging domains. He began with an overview of AlphaGo: the first program to defeat a professional player, and subsequently a world champion, in the game of Go - long viewed as the most challenging of classic games for AI.

He then moved on to discuss leading-edge developments in the Artificial Intelligence space, namely AlphaZero: an algorithm that learns entirely by self-play, without any human data or guidance. “The core idea is that AlphaZero can become its own teacher,” explained Professor Silver, “A neural network is trained both to predict AlphaZero’s own move selections and also to predict the winner of AlphaZero vs. AlphaZero games.”

“This neural network improves the strength of the tree search, resulting in higher quality move selection and stronger self-play games in the next iteration. Starting with a blank slate and given no domain knowledge except the game rules, within 24 hours AlphaZero achieved a superhuman level of play in the games of Go, chess and shogi (Japanese chess), and convincingly defeated the incumbent world-champion program in each case.”

Having graduated from the University of Cambridge in 1997 with the Addison-Wesley award. Subsequently, David co-founded the video games company Elixir Studios, where he was CTO and lead programmer, receiving several awards for technology and innovation.

David returned to academia in 2004 to study for a PhD on reinforcement learning with Rich Sutton, where he co-introduced the algorithms used in the first master-level 9x9 Go programs. David was awarded a Royal Society University Research Fellowship in 2011, and subsequently became a lecturer at University College London. David consulted for DeepMind from its inception, joining full-time in 2013.

His recent work has focused on combining reinforcement learning with deep learning, including a program that learns to play Atari games directly from pixels (Nature 2015). David led the AlphaGo project, culminating in the first program to defeat a top professional player in the full-size game of Go (Nature 2016), and the AlphaZero project, which learned by itself to defeat the world's strongest chess, shogi and Go programs (Nature 2017).

Read Professor David Silver’s full biography, or his research profile.

If you would like a copy of Professor Silver’s slides from his inaugural lecture, please contact computerscience.comms@ucl.ac.uk.