Latest

I am a Software Enginer at Google in the Seattle/Kirkland office. I work on Google's Hangouts.
I worked IBM Cognos as a software developer.

Teaching Assistant, COMP 424 Artificial Intelligence

My office hours are Tuesday, 10 to 11am at MC 112.

Current Location

I'm back in Montreal, working on POMDPs-related research.

Previous Location

I was a technical intern with IBM Extreme Blue Programme(Ottawa, Canada) from May to August 2010, where I work with a statistical analysis software(SPSS) to optimize customer support. Our work was presented at the IBM Headquarters in Armonk, New York.

Research

I am a Master's student studying Computer Science in McGill University. I am also a research assistant in the Reasoning and Learning Laboratory, under the supervison of Joelle Pineau I am primarily interested in Machine Learning and Artificial Intelligence.
I did my undergraduate degree in National University of Singapore, where I did research in the Adaptive Computing Laboratory. I helped to develop a software package, APPL(Approximate POMDP Planning Toolkit) , and design the POMDPX format. I spent almost 2 years of my undergraduate life doing research under the supervision of David Hsu and Lee Wee Sun.

Publications

  • S.W. Png, J.Pineau, and B. Chaib-draa. Buildling adaptive dialogue systems via Bayes-adaptive POMDP. In the IEEE Journal of Selected Topics in Signal Processing, vol.6(8) 2012
    BibTeX   PDF 
  • S.W. Png, and J.Pineau. Bayesian Reinforcement Learning for POMDP-based Dialogue Systems. In the International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011.
    BibTeX   PDF 
  • S.C.W. Ong, S.W. Png, D. Hsu, and W.S. Lee. Planning under Uncertainty for Robotic Tasks with Mixed Observability. In the International Journal of Robotics Research, 2010.
    BibTeX   PDF 
  • Y.Z. Du, D. Hsu, H. Kurniawati, W.S. Lee, S.C.W. Ong, and S.W. Png A POMDP Approach to Robot Motion Planning under Uncertainty. In Int. Conf. on Automated Planning & Scheduling, Workshop on Solving Real-World POMDP Problems, 2010.
    BibTeX   PDF 
  • S.C.W. Ong, S.W. Png, D. Hsu, and W.S. Lee. POMDPs for robotic tasks with mixed observability. In Proc. Robotics: Science and Systems, 2009.
    BibTeX   PDF 
  • Thesis

  • Undergraduate Thesis submitted to School of Computing, National University of Singapore 
  • Master's Thesis Bayesian Reinforcement Learning for POMDP-based Dialogue Systems submitted to School of Computer Science, McGill University This contains more scientific details and experimental results than the paper in ICASSP.
  •