Research interests

• Decision theory
• Reinforcement learning and Control
• Machine learning and Statistics
• Security and Privacy

Teaching

• Decision making under uncertainty 
  (Next: Tokyo Institute of Technology, Summer Term)
• Algorithms, data structures and logic (2014/2015 3)
• Artificial Intelligence (period 4, 2013/2014)
  

Upcoming events

• Machine Learning School (14-16 April 2015).
• RL Competition (volunteers needed)

Recent events

• Our paper On selecting the nonce length in distance bounding protocols received the Computer Journal Wilkes Award for 2014.
• AISec 2014. [Proceedings]
• Reinforcement learning tutorial at the MPI summer school on Autonomous Learning.
• ICML 2014 Workshop on Learning, Security and Priavacy.
• AISec 2013.

Projects

Recent papers

• Usable ABC Reinforcement Leanring. NIPS 2014, ABC in Montreal workshop.
• Generalised Entropy MDPs and Minimax Regret. NIPS 2014, From Bad Models to Good Policies Workshop.
• Expected loss bounds for authentication in constrained channels. Journal of Computer Security, 2014.
• On the Leakage of Information in Biometric Authentication, Indocrypt 2014.
• Robust and private Bayesian Inference. Algorithmic Learning Theory 2014.
• Distance bounding protocols: are you close enough? IEEE Security & Privacy Magazine.
• The Reinforcement Learning Competition, AI Magazine.
• Cover tree Bayesian reinforcement learning. Journal of machine learning research.
• Monte-Carlo utility estimates for Bayesian reinforcement learning, IEEE CDC 2013.
  
• Personalized news recommendation with context trees, RecSys 2013.
• Probabilistic inverse reinforcement learning in unknown environments, UAI 2013.
• ABC reinforcement learning, ICML 2013.
  
• Linear Bayesian reinforcement learning, IJCAI 2013.