Arthur Guez's Homepage

I am currently a Ph.D. student in the Gatsby Computational Neuroscience Unit (UCL, London, UK), where I am supervised by Peter Dayan and David Silver.

Previously, I was a M.Sc. student in Computer Science at McGill University in Montréal. My research supervisor was Joelle Pineau. I was part of the Reasoning and Learning lab and I was a member of the McGill Center for Intelligent Machines.

Thesis:

Guez, A. (2010) Adaptive control of epileptic seizures using reinforcement learning. M.Sc. Thesis, McGill University.

Journal papers:

Panuccio, G., Guez, A., Vincent, R., Avoli, M., Pineau, J. (2013) "Adaptive control of epileptiform excitability in an in vivo model of limbic seizures". Experimental Neurology.
[DOI]
Pineau, J., Guez, A., Vincent, R., and Avoli, M. (2009) Treating Epilepsy via Adaptive Neurostimulation: A Reinforcement Learning Approach. International Journal of Neural Systems. [LINK]

Conference papers:

Guez, A., Silver, D., and Dayan, P. (2012) Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search. Advances in Neural Information Processing Systems (NIPS).
(PDF including Supp.) [Videos] [Poster] [Code on GitHub]
Guez, A. and Pineau, J. (2010) Multi-Tasking SLAM. International Conference on Robotics and Automation (ICRA). [Video]
Guez, A., Vincent, R., Avoli, M. and Pineau, J. (2008) Adaptive Treatment of Epilepsy via Batch-mode Reinforcement Learning. Proceedings of the Twentieth Innovative Applications of Artificial Intelligence Conference (IAAI).

Workshop papers:

Guez, A., Silver, D., and Dayan, P. (2012) Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search. The 10th European Workshop on Reinforcement Learning (EWRL). Edinburgh, UK.
Guez, A. and Pineau, J. (2009) Performing Tasks while doing Simultaneous Localization And Mapping. NIPS Workshop on Probabilistic Approaches for Robotics and Control. Whistler, Canada. [poster]
Guez, A. and Pineau, J. (2009) Using Batch RL to Optimize Neurostimulation Strategies. Multidisciplinary Symposium on Reinforcement Learning. Montréal, Canada.
Paduraru, C., Guez, A., Precup, D., and Pineau, J. (2009) Model-based Bayesian Reinforcement Learning with Adaptive State Aggregation. Multidisciplinary Symposium on Reinforcement Learning. Montréal, Canada.
Bush, K., Pineau, J., Guez A., Vincent B., Panuccio G., and Avoli M. (2009) Dynamic Representations for Adaptive Neurostimulation Treatment of Epilepsy. 4th International Workshop on Seizure Prediction in Epilepsy. Kansas City, USA.
Vincent, R., Guez, A., Courville, A., Avoli, M., and Pineau, J. (2007) A computational model of epilepsy and response to electrical stimulation. 3rd International Workshop on Seizure Prediction in Epilepsy. Freiburg, Germany.

Teaching Assistant - Gatsby Unit's Unsupervised Learning course
Course Webpage: http://www.gatsby.ucl.ac.uk/teaching/courses/ml1-2011.html
Teaching Assistant - Gatsby Unit's Theoretical Neuroscience course
Course Webpage: http://www.gatsby.ucl.ac.uk/~aguez/tn1/
Teaching Assistant - McGill COMP 424 (Artificial Intelligence) Winter 2010
Course Webpage: http://www.cs.mcgill.ca/~dprecup/courses/ai.html

Ph.D. student, 2010-present, Gatsby Computational Neuroscience Unit, University College London.
M.Sc., McGill University, 2008-2010, Computer Science.
B.Sc., McGill University, 2008. Joint Honours Mathematics and Computer Science, Cognitive Science minor. Graduated with First Class Honours.

Arthur Guez