Selected Publications

Regularized Reinforcement Learning with Performance GuaranteesPaper
Mahdi Milani Fard, Ph.D. Thesis, Supervised by Joelle Pineau, 2014

Bellman Error Based Feature Generation using Random Projections on Sparse SpacesPaperAppendix
Mahdi Milani Fard, Yuri Grinberg, Amir-massoud Farahmand, Joelle Pineau, Doina Precup, Twenty-Seventh Conference on Neural Information Processing Systems, 2013 (NIPS'13)

Modelling Sparse Dynamical Systems with Compressed Predictive State RepresentationsPaper
William L. Hamilton, Mahdi Milani Fard, Joelle Pineau, The Thirtieth International Conference on Machine Learning, 2013 (ICML'13)

Bellman Error Based Feature Generation using Random Projections on Sparse SpacesPaper
Mahdi Milani Fard, Yuri Grinberg, Amir-massoud Farahmand, Joelle Pineau, Doina Precup, Technical Report, 2012

Random Projections Preserve Linearity in Sparse SpacesPaper
Mahdi Milani Fard, Yuri Grinberg, Joelle Pineau, Doina Precup, Technical Report, 2012

Compressed Least-Squares Regression on Sparse SpacesPaperSlides
Mahdi Milani Fard, Yuri Grinberg, Joelle Pineau, Doina Precup, Twenty-Sixth AAAI Conference on Artificial Intelligence, 2012 (AAAI'12)

Bellman Error Based Feature Generation Using Random ProjectionsPaperSlidesCode
Mahdi Milani Fard, Yuri Grinberg, Joelle Pineau, Doina Precup, Tenth European Workshop on Reinforcement Learning, 2012 (EWRL'12)

LSTD on Sparse SpacesPaper
Yuri Grinberg, Mahdi Milani Fard, Joelle Pineau, NIPS Workshop on New Frontiers in Model Order Selection, 2011

Least-Squares Regression on Sparse SpacesPaper
Yuri Grinberg, Mahdi Milani Fard, Joelle Pineau, NIPS Workshop on Sparse Representation and Low-rank Approximation, 2011

PAC-Bayesian Policy Evaluation for Reinforcement LearningPaper
Mahdi Milani Fard, Joelle Pineau, Csaba Szepesvári, Twenty-Seventh Conference on Uncertainty in Artificial Intelligence, 2011 (UAI'11)

Non-Deterministic Policies in Markovian Decision ProcessesPaper
Mahdi Milani Fard, Joelle Pineau, Journal of Artificial Intelligence Research, Volume 40, 2011

PAC-Bayesian Model Selection for Reinforcement LearningPaper
Mahdi Milani Fard, Joelle Pineau, Twenty-Forth Conference on Neural Information Processing Systems, 2010 (NIPS'10)

Measures of Uncertainty for Policy EvaluationPaper
Cosmin Paduraru, Doina Precup, Mahdi Milani Fard, North-Eastern Student Colloquim on Artificial Intelligence, 2010 (NESCAI'10)

Non-Deterministic Policies In Markovian ProcessesPaper
Mahdi Milani Fard, Masters Thesis, Supervised by Joelle Pineau, 2009

MDPs with Non-Deterministic PoliciesPaper
Mahdi Milani Fard, Joelle Pineau, Twenty-Second Conference on Neural Information Processing Systems, 2008 (NIPS'08)

A Variance Analysis for POMDP Policy EvaluationPaper
Mahdi Milani Fard, Joelle Pineau, Peng Sun, Twenty-Third AAAI Conference on Artificial Intelligence, 2008 (AAAI'08)

Behavioral Partitioning in a Hierarchical Mixture of Experts using K-Best-Experts Algorithm
Mahdi Milani Fard, A. Bakhtiary, IEEE Symposium on Foundations of Computational Intelligence, 2007 (FOCI'07)

Competitive Learning in an Ensemble of Local Experts
Mahdi Milani Fard, Caro Lucas, 12th International CSI Computer Conference, 2007 (CSICC'07)

A Co-evolutionary Competitive Multi-expert Approach to Image Compression with Neural Networks
Mahdi Milani Fard, IEEE International Conference on Engineering of Intelligent Systems, 2006 (ICEIS'06)

Collimator - Collaborative Image Annotator & Visual Concept Map Generator
A. Kashian, R. Kheng Leng Gay, H. Tatari, Mahdi Milani Fard, 5th International Semantic Web Conference, 2006 (ISWC'06)

Ensemble Learning with Local Experts
Mahdi Milani Fard, IEEE Computer Society ezine Looking.Forward student magazine 14th edition, 2006

Database Normalization, Before and After the Design
Mahdi Milani Fard, ENIAC Journal, Fall 2004