Satinder Singh is a Toyota Professor of Artificial Intelligence, Computer Science & Engineering Division, Electrical Engineering and Computer Science Department at University of Michigan, Ann Arbor.
Satinder's main research interest is in the old-fashioned goal of Artificial Intelligence (AI), that of building autonomous agents that can learn to be broadly competent in complex, dynamic, and uncertain environments. His deepest contributions are in RL and more recently in Deep RL. His research has also dealt with the challenge of building agents that can interact with other agents and even humans in both artificial and natural environments.
Tom Schaul has been a senior research scientist at DeepMind for 6 years. His research is focused on reinforcement learning with deep neural networks, but include modular and continual learning, black-box optimization, temporal and state abstractions, off-policy learning about many goals simultaneously, and video-game benchmarks. Tom grew up in Luxembourg and studied computer science in Switzerland (with exchanges at Waterloo and Columbia), where he obtained an MSc from the EPFL in 2005. He holds a PhD from TU Munich (2011), which he did under the supervision of Jürgen Schmidhuber at the Swiss AI Lab IDSIA. From 2011 to 2013, he did a postdoc with Yann LeCun at the Courant Institute of NYU.
Doina Precup is a Faculty Member at Mila, Associate Professor, School of Computer Science, McGill University; CIFAR Senior Fellow, Program in Learning in Machines and Brains; Associate Scientific Director, Healthy Brains for Healthy Lives CFREF; and also is the Research Team Lead at DeepMind, Montreal
Doina Precup received her B.Sc. from the Computer Science Department, Technical University Cluj-Napoca, Romania, in 1994, and the M.S. and PhD from the Department of Computer Science, University of Massachusetts, Amherst, in 1997 and 2000 respectively. Doina Precup's research interests lie mainly in the field of machine learning. She is especially interested in the learning problems that face a decision-maker interacting with a complex, uncertain environment. Doina uses the framework of reinforcement learning to tackle such problems. Her current research is focused on developing better knowledge representation methods for reinforcement learning agents.