Publications

Cosmin Paduraru (2013)
"Off-policy Evaluation in Markov Decision Processes" .pdf ]
PhD Thesis, McGill University
(Note: This is a more compactly formatted version of the pdf I officially submitted to McGill.)

Cosmin Paduraru, Doina Precup, Joelle Pineau and Gheorghe Comanici (2012)
"An Empirical Analysis of Off-policy Learning in Discrete MDPs" .pdf ]
Proceedings of the 10th European Workshop on Reinforcement Learning

Cosmin Paduraru, Doina Precup, and Joelle Pineau (2011)
"A Framework for Computing Bounds for the Return of a Policy" .pdf ]
Proceedings of the 9th European Workshop on Reinforcement Learning

Cosmin Paduraru, Daniel J. Lizotte, Doina Precup, and Joelle Pineau (2011)
"Adding Foresight to Decision-Making in Health Care: The Reinforcement Learning Approach" .pdf ]
ICML Workshop on Machine Learning for Global Challenges

Cosmin Paduraru, Doina Precup, and Mahdi Milani Fard. (2010)
"Measures of Uncertainty for Policy Evaluation" [ .pdf ]
North-Eastern Student Colloquim on Artificial Intelligence

Cosmin Paduraru, Doina Precup, Stephane Ross, and Joelle Pineau (2008)
"Model-based Bayesian Reinforcement Learning with Tree-based State Aggregation" [ .pdf ]
NIPS Workshop on Model Uncertainty and Risk in Reinforcement Learning
 
Cosmin Paduraru, Robert Kaplow, Doina Precup, and Joelle Pineau (2008)
"Model-based Reinforcement Learning with State Aggregation" [ .pdf ]
8th European Workshop on Reinforcement Learning
 
Cosmin Paduraru (2007)
"Planning with Approximate and Learned Models of Markov Decision Processes" [ .pdf ]
MSc Thesis, University of Alberta
 
Brian Tanner, Vadim Bulitko, Anna Koop, and Cosmin Paduraru (2007)
"Grounding Abstractions in Predictive State Representations" [ .pdf ]
Proceedings of the Twentieth International Joint Conference on Artificial Intelligence (IJCAI 07)
 
Doina Precup, Richard S. Sutton, Cosmin Paduraru, Anna Koop, and Satinder Singh (2006)
"Off-policy Learning with Options and Recognizers" [ .pdf ]
Proceedings of the 19th Annual Conference on Neural Processing Information Systems (NIPS 05)
 
Cosmin Paduraru and Vadim Bulitko (2005)
"Supervised Learning of Options: A Pilot Study" [ .pdf ]
Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (IJCAI 05), Workshop on Planning and Learning in A Priori Unknown or Dynamic Domains