I am a postdoctoral fellow with the Alberta Ingenuity Centre for Machine Learning (AICML), at the Department of Computing Science, University of Alberta, Edmonton, Canada.

I am also an Alberta Ingenuity research fellow.

Publications

• Bayesian Actor-Critic Algorithms. ICML (2007), with Mohammad Ghavamzadeh. PS, PDF
• Bayesian Policy Gradient Algorithms. NIPS (2006), with Mohammad Ghavamzadeh. PS, PDF
• Learning to Control an Octopus Arm with Gaussian Process Temporal Difference Methods. NIPS (2005), with Peter Szabo and Dmitry Volkinshtein. PS, PDF
• Learning Wireless Network Association-Control with Gaussian Process Temporal Difference Methods. OPNETWORK (2005), with Nadav Aharony and Tzachy Zehavi. PS, PDF (Best Technical Paper Award).
• Reinforcement Learning with Gaussian Processes. ICML (2005), with Shie Mannor and Ron Meir. PS, PDF
• Algorithms and Representations for Reinforcement Learning. Ph.D. Thesis, (2005). PS, PDF
• A Dynamic Model of the Octopus Arm. I. Biomechanics of the Octopus Reaching Movement. Journal of Neurophysiology 94: 1443-1458 (2005), with Y. Yekutieli, R. Sagiv-Zohar, R. Aharonov, B. Hochner and T. Flash. PDF
• The Kernel Recursive Least Squares Algorithm . IEEE Transactions on Signal Processing (2004), Vol.52, Issue 8, with Shie Mannor and Ron Meir.
• Bayes Meets Bellman: The Gaussian Process Approach to Temporal Difference Learning . ICML (2003), with Shie Mannor and Ron Meir (Best Student Paper Award).
• The Kernel Recursive Least Squares Algorithm . ICNC Technical Report ICNC-03-001 (2003), with Shie Mannor and Ron Meir.
• Sparse Online Greedy Support Vector Regression ECML (2002), with Shie Mannor and Ron Meir. PS, PDF
• Learning Embedded Maps of Markov Processes ICML (2001), with Shie Mannor. PS, PDF
• On Finding Good State Aggregation Functions . Workshop on Hierarchy and Memory in Reinforcement Learning, ICML (2001), with Shie Mannor. PS , PDF
• A Dynamical Model of the Octopus Arm. Neuroscience letters. Supl. 48. Proceedings of the 6th annual meeting of the Israeli Neuroscience Society (1997), with Ranit Aharonov, Benny Hochner and Tamar Flash.

Talks

• Bayesian Actor-Critic Algorithms (AI Seminar) PS , PDF
• Bayesian RL Tutorial -- Gaussian Process Temporal Difference Learning (ICML'07) PS , PDF, Video
• Bayesian RL Tutorial -- Octopus Arm Demo (ICML'07) PS , PDF, Video
• Learning to Control an Octopus Arm with Gaussian Process Temporal Difference Methods (Gaussian Processes in Practice Workshop 2006) PS , PDF, Video
• Reinforcement Learning with Gaussian Processes (ICML'05) PS , PDF
• Reinforcement Learning with Gaussian Processes (RLAI Talk) PS , PDF
• Reinforcement Learning with Gaussian Processes (Long version) PS , PDF
• The Gaussian Process Approach to Temporal Difference Learning (ICML'03) PS , PDF
• Sparse Online Greedy Support Vector Regression (ECML'02) PS , PDF
• Learning Embedded Maps of Markov Processes (ICML'01) PS , PDF

Projects

• Learning to Control an Octopus Arm with Gaussian Process Temporal Difference Methods
Project report PDF
• Learning Wireless Network Association-Control with Gaussian Process Temporal Difference Methods
Project report PDF

Code

• Kernel Recursive Least Squares (KRLS)  -  C source code and documentation
  
• Heuristic Embedding of Markov Processes (HEMP)  -  C source code
  

Yaakov Engel
AICML, Department of Computing Science
2-21 Athabasca Hall, University of Alberta
Edmonton, Alberta, Canada T6G 2E8
Tel: (780) 492-5062
Fax: (780) 492-1071
Email:

Visitor number:  Powered by counter.bloke.com