Search Machine Learning Repository:
All publications by Doina Precup
authors venues years



Variational Generative Stochastic Networks with Collaborative Shaping
Philip Bachman and Doina Precup
Proceedings of the 32nd International Conference on Machine Learning (ICML-15), 2015


Data Generation as Sequential Decision Making
Philip Bachman and Doina Precup
Advances in Neural Information Processing Systems 28, 2015


Basis refinement strategies for linear value function approximation in MDPs
Gheorghe Comanici, Doina Precup and Prakash Panangaden
Advances in Neural Information Processing Systems 28, 2015


A new Q(lambda) with interim forward view and Monte Carlo equivalence
Rich Sutton, Ashique R. Mahmood, Doina Precup and Hado V. Hasselt
Proceedings of the 31st International Conference on Machine Learning (ICML-14), 2014


Sample-based approximate regularization
Philip Bachman, Amir-massoud Farahmand and Doina Precup
Proceedings of the 31st International Conference on Machine Learning (ICML-14), 2014


Learning with Pseudo-Ensembles
Phil Bachman, Ouais Alsharif and Doina Precup
Advances in Neural Information Processing Systems 27, 2014


Optimizing Energy Production Using Policy Search and Predictive State Representations
Yuri Grinberg, Doina Precup and Michel Gendreau
Advances in Neural Information Processing Systems 27, 2014


Bellman Error Based Feature Generation using Random Projections on Sparse Spaces
Mahdi M. Fard, Yuri Grinberg, Amir M. Farahmand, Joelle Pineau and Doina Precup
Advances in Neural Information Processing Systems 26, 2013


Learning from Limited Demonstrations
Beomjoon Kim, Amir M. Farahmand, Joelle Pineau and Doina Precup
Advances in Neural Information Processing Systems 26, 2013


Average Reward Optimization Objective In Partially Observable Domains
Yuri Grinberg and Doina Precup
Proceedings of the 30th International Conference on Machine Learning (ICML-13), 2013


On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization
Doina Precup, Joelle Pineau and Andre S. Barreto
Advances in Neural Information Processing Systems 25, 2012


Value Pursuit Iteration
Amir M. Farahmand and Doina Precup
Advances in Neural Information Processing Systems 25, 2012


Improved Estimation in Time Varying Models
Doina Precup and Philip Bachman
Proceedings of the 29th International Conference on Machine Learning (ICML-12), 2012


On Average Reward Policy Evaluation in Infinite-State Partially Observable Systems
Yuri Grinberg and Doina Precup
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS-12), 2012


Reinforcement Learning using Kernel-Based Stochastic Factorization
Andre S. Barreto, Doina Precup and Joelle Pineau
Advances in Neural Information Processing Systems 24, 2011


Approximate Predictive Representations of Partially Observable Systems
Monica Dinculescu and Doina Precup
Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010


Fast gradient-descent methods for temporal-difference learning with linear function approximation
Richard S. Sutton, Hamid R. Maei, Doina Precup, Shalabh Bhatnagar, David Silver, Csaba Szepesvári and Eric Wiewiora
Proceedings of the 26th International Conference on Machine Learning (ICML-09), 2009


Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation
Shalabh Bhatnagar, Doina Precup, David Silver, Richard S. Sutton, Hamid R. Maei and Csaba Szepesvári
Advances in Neural Information Processing Systems 22, 2009


Reinforcement learning in the presence of rare events
Jordan Frank, Shie Mannor and Doina Precup
Proceedings of the 25th International Conference on Machine Learning (ICML-08), 2008


Bounding Performance Loss in Approximate MDP Homomorphisms
Jonathan Taylor, Doina Precup and Prakash Panagaden
Advances in Neural Information Processing Systems 21, 2008


Automatic basis function construction for approximate dynamic programming and reinforcement learning
Philipp W. Keller, Shie Mannor and Doina Precup
Proceedings of the 23th International Conference on Machine Learning (ICML-06), 2006


Off-policy Learning with Options and Recognizers
Doina Precup, Cosmin Paduraru, Anna Koop, Richard S. Sutton and Satinder P. Singh
Advances in Neural Information Processing Systems 18, 2005


Combining TD-learning with Cascade-correlation Networks
Françcois Rivest and Doina Precup
Proceedings of the 20th International Conference on Machine Learning (ICML-03), 2003


A Convergent Form of Approximate Policy Iteration
Theodore J. Perkins and Doina Precup
Advances in Neural Information Processing Systems 15, 2002