Publications
- PAC Optimal Exploration in Continuous Space Markov Decision Processes, Jason Pazis and Ronald Parr, Proceedings of the Twenty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2013, Bellevue, Washington, USA, July 14-18, 2013 (Honorable Mention award)
- Sample Complexity and Performance Bounds for Non-parametric Approximate Linear Programming, Jason Pazis and Ronald Parr, Proceedings of the Twenty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2013, Bellevue, Washington, USA, July 14-18, 2013
- Non-parametric Approximate Linear Programming for MDPs, Jason Pazis and Ronald Parr, Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2011, San Francisco, California, USA, August 7-11, 2011
- Generalized Value Functions for Large Action Sets, Jason Pazis and Ronald Parr, Proceedings of the 28th International Conference on Machine Learning (ICML-11), Bellevue, Washington, USA, June 2011
- Reinforcement Learning in Multidimensional Continuous Action Spaces, Jason Pazis and Michail G. Lagoudakis, 2011 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), Paris, France, April 2011
- Binary Action Search for Learning Continuous-Action Control Policies, Jason Pazis and Michail G. Lagoudakis, Proceedings of the 26th International Conference on Machine Learning (ICML-09), Montreal, Canada, June 2009
- Learning Continuous-Action Control Policies, Jason Pazis and Michail G. Lagoudakis, 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), Nashville, TN, USA, March 2009