My research interests include (modular) reinforcement learning, stochastic (black-box) optimization with minimal hyperparameter tuning, and (deep/recurrent) neural networks. I use these techniques in application domains ranging from computer vision and neural decoding to games and robotics.
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.
|ICML 2013||T. Schaul, S. Zhang, Y. LeCun. No more Pesky Learning Rates.
International Conference on Machine Learning. [Pdf] [Supplementary material] [Code] [BibTeX]
|IJCAI 2013||T. Schaul, M. Ring. Better Generalization with Forecasts.
International Joint Conference on Artificial Intelligence. [Pdf] [Slides] [BibTeX]
|ICLR 2013||T. Schaul, Y. LeCun. Adaptive Learning Rates and Parallelization for Stochastic, Sparse, Non-smooth Gradients.
International Conference on Learning Representations. [Pdf] [Code] [Public reviews] [BibTeX]
|CIG 2013||T. Schaul. A Video Game Description Language for Model-based or Interactive Learning.
IEEE Conference on Computational Intelligence in Games. [Pdf] [Code] [BibTeX]
|GECCO 2012||T. Schaul. Natural Evolution Strategies Converge on Sphere Functions.
Genetic and Evolutionary Computation Conference. [Pdf] [BibTeX]
|IJCAI 2011||M. Ring, T. Schaul. Q-error as a Selection Mechanism in Modular Reinforcement-Learning Systems.
International Joint Conference on Artificial Intelligence. [Pdf] [BibTeX]
|JMLR 2010||T. Schaul, J. Bayer, D. Wierstra, Y. Sun, M. Felder, F. Sehnke, T. Rückstieß, J. Schmidhuber. PyBrain.
Journal of Machine Learning Research. [Pdf] [BibTeX]
|ICML 2009||Y. Sun, D. Wierstra, T. Schaul, J. Schmidhuber. Stochastic Search using the Natural Gradient.
International Conference on Machine Learning. [Pdf] [BibTeX]