Tom Schaul

Tom Schaul, Ph.D.

I am a senior staff research scientist at DeepMind London.

My research interests include (modular/hierarchical) reinforcement learning, (stochastic/black-box) optimization with minimal hyperparameter tuning, and (deep/recurrent) neural networks. My favorite application domain are games.

I grew up in Luxembourg and studied computer science in Switzerland (with exchanges at Waterloo and Columbia), where I obtained an MSc from the EPFL in 2005. I hold a PhD from TU Munich (2011), which I did under the supervision of Jürgen Schmidhuber at the Swiss AI Lab IDSIA. From 2011 to 2013 I was a postdoc at the Courant Institute of NYU, in the lab of Yann LeCun.

Selected papers

NeurIPS 2022 T. Schaul, A. Barreto, J. Quan and G. Ostrovski. The Phenomenon of Policy Churn.
Advances in Neural Information Processing Systems. [arXiv]
Nature Comm. 2020 N. Tomašev, J. Cornebise, F. Hutter et al. AI for Social Good: Unlocking the Opportunity for Positive Impact.
Nature Communications 11 (2468). [Link]
Nature 2019 O. Vinyals, I. Babuschkin, W. Czarnecki et al. Grandmaster level in StarCraft II using multi-agent reinforcement learning.
Nature 574 (7780). [Link] [Preprint] [Blog] [Video]
RLDM 2019 T. Schaul, D. Borsa, J. Modayil and R. Pascanu. Ray Interference: a Source of Plateaus in Deep Reinforcement Learning.
Multidisciplinary Conference on Reinforcement Learning and Decision Making . [arXiv]
ICLR 2016

T. Schaul, J. Quan, I. Antonoglou and D. Silver. Prioritized Experience Replay.
International Conference on Learning Representations. [arXiv][BibTeX]

ICML 2015

T. Schaul, D. Horgan, K. Gregor and D. Silver. Universal Value Function Approximators.
International Conference on Machine Learning. [Pdf] [BibTeX]

See the full list of publications for 50+ additional ones.