Eric Wiewiora

eric.wiewiora@gmail.com

Research Interests

• Reinforcment Learning Theory
• Exploration versus Exploitation
• Value function approximation
• Structured Policies
• Unsupervised Learning
• Predictive representations of dynamical systems
• Learning structure of time series
• Clustering
• Planning and Scheduling Algorithms
• Statistical Learning Theory
• Learning Motor Control

Education

• PhD from the University of California, San Diego 2007
  • Dissertation: Modeling Probability Distributions with Predictive State Representations
• MS from the Unversity of California, San Diego, 2004
• BAS in Computer Science from the University of Pittsburgh
  • Thesis Topic: Efficient Exploration for Reinforcement Learning

Publications

1. Bala Kalyanasundarum and Eric Wiewiora. "Dynamic Spectrum Allocation" University of Pittsburgh Undergraduate Research Fair. March, 2000.
2. Kirk Pruhs and Eric Wiewiora. "Evaluating the Local Ratio Algorithm for Dynamic Storage", 4th Workshop on Algorithm Engineering and Experiments Jan 2002.
3. Eric Wiewiora, Garrison Cottrell and Charles Elkan. "Principled Methods for Advising Reinforcement Learning Agents", Proceedings of the Twentieth International Conference on machine Learning. August, 2003.
4. Eric Wiewiora. "Potential-Based Shaping and Q-Value Initialization are Equivalent", Journal of Artificial Intelligence Research, 2003.
5. Eric Wiewiora. "Learning Predictive Representations from a History" Proceedings of the Twentysecond International Conference on Mchine Learning. 2005
6. Alex Strehl, Lihong Li, Eric Wiewiora, John Langford and Micheal Littman. "PAC Model-free Reinforcement Learning" Proceedings of the Twenty-third International Conference on Machine Learning. 2006.
7. Andrew Rabinovich, Andrea Vedaldi, Carolina Galleguillos, Eric Wiewiora and Serge Belongie. "Objects in Context", Proceedings of the International Conference on Computer Vision. 2007.