Dr Søren Riis

Queen Mary University of London.

Søren Riis has more than 15 years of experience in teaching computability, complexity and the art of creating fast efficient algorithms. He has a strong interest in reinforcement learning and generative adversarial networks (GANs) related to strategy games. Riis has been actively involved in computer chess, and is listed on the wiki of influential people in chess programming https://www.chessprogramming.org/

Søren Riis is a strong player of strategy games including Chess, Shogi, Go and Bridge at an internal level. He has worked as a consultant for an AI company and is involved in applying deep learning for the card game of bridge.

For the last 5 years he has been working on technical projects related to machine learning and reinforcement learning. He has practical experience and interest in scientific computing on super computers, and in creating C and C++ libraries to run from within python. Søren Riis is particularly interested in supervising students with a strong technical and/or maths background. Aptitude for strategy games with an interest in one the following ares is an advantage.

  • Games requiring inductive reasoning combined with exploration.
  • Hidden identity games (Werewolf, Resistance/Avalon, Mafia etc)
  • Using GANs to sample realistic scenarios during gameplay
  • Deep Reinforcement Learning in multi-agent strategy games
  • Building and analysing games for investigating evolution of communication.

Research themes:

  • Game AI
  • Game Design
  • Game Creativity 
  • Games and mathematics